© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15582
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially those relating to statistical significance and appearing in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    foreign or non-English terms

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

    0

    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
    Negative Logits
     bright
    -1.10
     brilliant
    -0.95
    bright
    -0.88
     Bright
    -0.81
     Brilliant
    -0.77
     brillant
    -0.75
    brilliant
    -0.74
     genius
    -0.73
     BRIGHT
    -0.71
     smart
    -0.70
    POSITIVE LOGITS
     متعلقه
    0.96
    UIControlState
    0.83
    ValueStyle
    0.77
     Efq
    0.75
    ագրություններ
    0.73
     GenerationType
    0.73
     bezeichneter
    0.70
    WireFormatLite
    0.69
    UrlEncoded
    0.69
     الدولى
    0.69
    Activations Density 2.623%

    No Known Activations