© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7472
    Prev
    Next
    INDEX
    Explanations

    characters and syntax commonly found in computer code

    oai_token-act-pair · gemini-2.0-flash

    archaic or unusual spelling patterns

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -1.31
     (
    -1.02
     
    -1.01
    ,
    -0.98
     a
    -0.94
     the
    -0.92
     B
    -0.92
     [
    -0.91
    ...
    -0.88
    ’
    -0.88
    POSITIVE LOGITS
     itſelf
    1.90
     Theſe
    1.86
     Monfieur
    1.73
     myſelf
    1.70
     raiſ
    1.56
    expandindo
    1.55
     faſt
    1.50
     crdi
    1.48
     Reſ
    1.47
     uſed
    1.45
    Activations Density 5.134%

    No Known Activations