© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4326
    Prev
    Next
    INDEX
    Explanations

    words specific to categories such as sports, biology, geography, and coding.

    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
    <bos>
    -0.75
     Theſe
    -0.75
     typelib
    -0.73
    ſelf
    -0.71
     médié
    -0.68
     Monfieur
    -0.68
     Проци
    -0.67
     doInBackground
    -0.67
     itſelf
    -0.66
     himſelf
    -0.65
    POSITIVE LOGITS
    osti
    0.46
     Ros
    0.45
     Dug
    0.44
     Sti
    0.44
    bira
    0.43
    fort
    0.43
    :✨
    0.43
     Giải
    0.42
    kend
    0.42
    pu
    0.42
    Activations Density 20.315%

    No Known Activations