© 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 · 56-GEMMASCOPE-2-TRANSCODER-262K · 24622 ｜ Neuronpedia
Home
Gemma-3-27B-IT
56-GEMMASCOPE-2-TRANSCODER-262K
24622
Prev
Next
MODEL
56-gemmascope-2-transcoder-262k
Source/SAE
INDEX
Go
Explanations
specific items
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_56_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/56-gemmascope-2-transcoder-262k/24622?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/56-gemmascope-2-transcoder-262k/24622?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
되어
1.05
되어
1.02
になって
0.79
돼
0.73
ようになって
0.70
くなって
0.59
나와
0.57
져
0.57
돼
0.56
となって
0.56
POSITIVE LOGITS
da
0.40
da
0.39
receita
0.39
সঙ্ক
0.38
ດ
0.38
ታት
0.38
ita
0.37
دا
0.37
زین
0.36
ViewData
0.36
Act
ivations
Density 0.002%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
