© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13145
    Prev
    Next
    INDEX
    Explanations

    mentions of magazine issues or editions

    oai_token-act-pair · gemini-2.0-flash

    4 or 8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    出版年
    -0.81
    EndGlobalSection
    -0.69
    parsedMessage
    -0.63
    poons
    -0.62
    GraphicsUnit
    -0.61
    ArgsConstructor
    -0.59
    EDEFAULT
    -0.57
    FilterChain
    -0.57
    encodeWith
    -0.57
    ´)
    -0.56
    POSITIVE LOGITS
    chaqueta
    0.51
     acceptez
    0.50
     transférez
    0.50
     meille
    0.50
     yourselves
    0.46
     Mexicana
    0.45
     Monfieur
    0.45
     espoir
    0.45
     Efq
    0.43
     distributed
    0.43
    Activations Density 0.630%

    No Known Activations