© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
GEMMA-3-27B-IT · 59-GEMMASCOPE-2-TRANSCODER-262K · 151602 ｜ Neuronpedia
Home
Gemma-3-27B-IT
59-GEMMASCOPE-2-TRANSCODER-262K
151602
Prev
Next
MODEL
59-gemmascope-2-transcoder-262k
Source/SAE
INDEX
Go
Explanations
<start_of_turn>
np_max-act-logits · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-27b-it/59-gemmascope-2-transcoder-262k/151602?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-27b-it/59-gemmascope-2-transcoder-262k/151602?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
rafa
0.40
|");
0.38
*>
0.36
-/
0.36
|)
0.35
是我
0.35
lump
0.34
手中的
0.34
/}
0.34
是我们
0.33
POSITIVE LOGITS
kan
0.80
Kan
0.77
Kan
0.75
om
0.71
Om
0.64
kan
0.64
Om
0.62
Het
0.61
og
0.60
KAN
0.59
Act
ivations
Density 0.001%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
