Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
21-GEMMASCOPE-TRANSCODER-16K
11041
Prev
Next
MODEL
21-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
verbs associated with obtaining or manipulating objects or information.
oai_token-act-pair · gemini-2.0-flash
No Scores
variations of "it"
np_token-act-pair-logits · gpt-4o-mini
No Scores
variations of "it"
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope/layer_21/width_16k
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/11041?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/11041?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
its
-0.71
ITS
-0.68
Its
-0.66
Its
-0.62
shes
-0.62
ITS
-0.60
hes
-0.59
suo
-0.59
its
-0.59
theres
-0.57
POSITIVE LOGITS
it
2.80
It
1.64
It
1.56
it
1.38
มัน
1.15
آن
1.01
nó
0.95
它
0.94
それは
0.91
ello
0.86
Act
ivations
Density 3.375%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
