© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3752
    Prev
    Next
    INDEX
    Explanations

    words associated with the US Senate and legislative processes

    oai_token-act-pair · gemini-2.0-flash

    bill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Vidite
    -0.95
    webElementXpaths
    -0.93
    parsedMessage
    -0.91
    CloseOperation
    -0.91
    脚注の使い方
    -0.88
     betweenstory
    -0.88
     esternos
    -0.87
     estekak
    -0.85
    RTEE
    -0.85
     AssemblyCompany
    -0.84
    POSITIVE LOGITS
     fig
    0.45
     serial
    0.45
    fig
    0.38
    SERIAL
    0.36
     nam
    0.34
    serial
    0.34
     plu
    0.34
     Serial
    0.34
    ново
    0.34
     ch
    0.33
    Activations Density 15.631%

    No Known Activations