© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13628
    Prev
    Next
    INDEX
    Explanations

    words related to government funding and priorities, especially at the state level

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    sendFile
    -0.62
    pinch
    -0.59
    DockStyle
    -0.56
    train
    -0.55
    ensement
    -0.54
     faro
    -0.53
     pinch
    -0.52
    erals
    -0.52
    stickers
    -0.52
     Meksiku
    -0.52
    POSITIVE LOGITS
    __*/
    0.57
    makeConstraints
    0.57
    abestanden
    0.47
     EXTERNAL
    0.47
     externos
    0.46
    EXTERN
    0.46
     bParam
    0.45
     transfieras
    0.45
    ViewImports
    0.45
    erçe
    0.44
    Activations Density 1.969%

    No Known Activations