© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6406
    Prev
    Next
    INDEX
    Explanations

    words related to telling stories and who wrote them

    oai_token-act-pair · gemini-2.0-flash

    tokens related to telling stories

    np_token-act-pair-logits · gpt-4o-mini

    telling stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ostavi
    -0.68
    цездатний
    -0.68
    脚注の使い方
    -0.66
     يتيمه
    -0.66
    MigrationBuilder
    -0.62
    الدراسه
    -0.61
    IntoConstraints
    -0.59
     beginnetje
    -0.59
     quadrangle
    -0.56
    FormTagHelper
    -0.56
    POSITIVE LOGITS
    roek
    0.52
     eleg
    0.45
    https
    0.45
     https
    0.45
     huyền
    0.45
    yaar
    0.45
    utzung
    0.44
    ;#
    0.44
     consultato
    0.44
    Források
    0.43
    Activations Density 3.528%

    No Known Activations