© 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. 9939
    Prev
    Next
    INDEX
    Explanations

    words relating to aircraft and flying, and locations related to aviation

    oai_token-act-pair · gemini-2.0-flash

    aviation

    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
     InputDecoration
    -0.86
    LookAnd
    -0.75
     виправивши
    -0.73
     planes
    -0.73
    planes
    -0.71
    ptid
    -0.71
    LLocation
    -0.70
    aarrggbb
    -0.70
     ComVisible
    -0.69
     MenuView
    -0.69
    POSITIVE LOGITS
     selezione
    0.46
     Ressources
    0.43
    XtraReports
    0.43
     đạp
    0.42
    fige
    0.40
     tahap
    0.39
    copg
    0.39
    гії
    0.38
     weten
    0.38
     memen
    0.38
    Activations Density 3.286%

    No Known Activations