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
20-GEMMASCOPE-TRANSCODER-16K
14262
Prev
Next
MODEL
20-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
Java-related error messages, especially those indicating problems with class initialization
oai_token-act-pair · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.20.ln2.hook_normalized
Architecture
jumprelu_transcoder
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-transcoder-16k/14262?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-transcoder-16k/14262?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Efq
-1.26
myſelf
-1.12
Monfieur
-1.08
itſelf
-1.04
uſed
-1.03
ſelves
-1.02
whoſe
-1.02
raiſ
-1.01
Reſ
-1.00
Houſe
-1.00
POSITIVE LOGITS
A
0.52
C
0.45
P
0.45
R
0.42
H
0.39
`
0.38
as
0.37
0.37
E
0.37
c
0.37
Act
ivations
Density 0.099%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
