© 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. 12466
    Prev
    Next
    INDEX
    Explanations

    mentions of policies and decisions made in a school and/or government setting

    oai_token-act-pair · gemini-2.0-flash

    debate and decision making

    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
    ubi
    -0.45
    ver
    -0.40
     Zacks
    -0.40
    closed
    -0.39
    engar
    -0.39
    гур
    -0.39
    Géographie
    -0.38
    putBoolean
    -0.37
    vdots
    -0.37
    ()));
    -0.37
    POSITIVE LOGITS
    uestamente
    0.72
    StoreMessageInfo
    0.70
    awtextra
    0.67
     Infórmanos
    0.64
     AssemblyProduct
    0.62
     myſelf
    0.60
     mwenye
    0.60
     Paglinawan
    0.59
     الحره
    0.59
    älfte
    0.59
    Activations Density 2.029%

    No Known Activations