© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9597
    Prev
    Next
    INDEX
    Explanations

    partial word matches to "muslims", "dale", "darcy", and "finger"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pas
    -0.47
     
    -0.47
     per
    -0.47
    {\
    -0.46
     total
    -0.44
     ${\
    -0.43
     len
    -0.43
    </i>
    -0.42
     ac
    -0.41
     sur
    -0.41
    POSITIVE LOGITS
    __':
    1.02
    __':
    0.98
    yntaxException
    0.94
    endpush
    0.91
    __":
    0.90
    <bos>
    0.87
    __":
    0.86
    AsUp
    0.84
    StoryboardSegue
    0.83
    ValueStyle
    0.82
    Activations Density 0.530%

    No Known Activations