© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10840
    Prev
    Next
    INDEX
    Explanations

    scientific or medical jargon

    oai_token-act-pair · gemini-2.0-flash

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    aarrggbb
    -0.84
    DockStyle
    -0.71
    UnusedPrivate
    -0.69
     الحره
    -0.68
    AsUp
    -0.68
     Seeder
    -0.68
    adaptiveStyles
    -0.67
    PerformLayout
    -0.63
     ProtoMessage
    -0.62
    tagext
    -0.62
    POSITIVE LOGITS
    Cordialement
    0.51
    ArgsConstructor
    0.48
    agues
    0.47
    ILLES
    0.46
     those
    0.46
    enor
    0.45
    ruptedException
    0.45
    mine
    0.45
     glück
    0.44
     bornes
    0.44
    Activations Density 13.056%

    No Known Activations