© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3304
    Prev
    Next
    INDEX
    Explanations

    non-English language text and possibly recognizes components of legal language

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     himo
    -0.79
    enumii
    -0.74
    AutoField
    -0.72
    انيف
    -0.71
    AsUp
    -0.70
    InstanceState
    -0.70
    ########.
    -0.68
     typelib
    -0.68
     незавершена
    -0.67
    ttino
    -0.65
    POSITIVE LOGITS
    inheritDoc
    0.48
     vàng
    0.45
    chier
    0.45
     Neub
    0.45
    missione
    0.44
    cum
    0.44
    itola
    0.43
    シップ
    0.42
    zzata
    0.42
    ccion
    0.42
    Activations Density 9.137%

    No Known Activations