Not that a rollout will answer the question, but here it is anyway.
I'm often a bit reluctant to offer a cube when leading 4a 2a since it gives up the advantage of being ahead in the score and makes the entire match turn on the current game. But, ignoring gammons, the take point for the trailer is only a bit lower than normal at ~19%. (and gammons don't really matter for the take decision) Here, playing against a not-very-skilled player I waited until I was fairly sure I had a cash, missing "theoretical" cubes the previous two rolls. I mean, who takes this one?
Well, my opponent did, and proceeded to throw an early six followed by unanswered doubles to win the match. But you probably already guessed the outcome.
                       |
| ||||
| XGID=-aDCCBB-A--------------ck-:0:0:1:00:3:1:0:5:9 | |||||
| Blue on roll, cube action? | |||||
| Analyzed in Rollout | No double | Double/Take |
| Player Winning Chances: | 87.40% (G:1.97% B:0.02%) | 87.55% (G:1.55% B:0.02%) |
| Opponent Winning Chances: | 12.60% (G:0.03% B:0.00%) | 12.45% (G:0.04% B:0.00%) |
| Cubeless Equities | +0.782 | +2.147 |
| Cubeful Equities | ||
| No double: | +0.902 (-0.098) | ±0.002 (+0.900..+0.904) |
| Double/Take: | +1.569 (+0.569) | ±0.005 (+1.563..+1.574) |
 Double/Pass: | +1.000 | |
| Best Cube action: Double / Pass | ||
| Rollout details | ||
| 1296 Games rolled with Variance Reduction. Moves: 3-ply, cube decisions: XG Roller | ||
| Double Decision confidence: | 100.0% | |
| Take Decision confidence: | 100.0% | |
| Duration: 1.3 seconds | ||
eXtreme Gammon Version: 2.10, MET: Kazaross XG2