© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14733
    Prev
    Next
    INDEX
    Explanations

    french words related to asking questions or making comparisons

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to coding or programming

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

    comme

    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
     as
    -0.53
    ToBounds
    -0.48
     impug
    -0.46
     like
    -0.44
    renia
    -0.43
     stump
    -0.43
     noexcept
    -0.43
     Necessity
    -0.41
    lossus
    -0.41
     ممت
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.97
    AndEndTag
    0.80
    FieldBuilder
    0.75
    BeginInit
    0.73
     وتسجيلات
    0.72
    ⓧ
    0.72
    mergeFrom
    0.71
     AssemblyCulture
    0.68
     Référence
    0.66
    GEBURTSDATUM
    0.63
    Activations Density 0.424%

    No Known Activations