© 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. 8463
    Prev
    Next
    INDEX
    Explanations

    references to dates and numbers in years

    oai_token-act-pair · gemini-2.0-flash

    foreign language or technical terms

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

    movies and TV plots

    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
     régulière
    -0.66
     Shakspeare
    -0.59
     LXXX
    -0.59
     itſelf
    -0.57
     Mauritania
    -0.57
     wireType
    -0.57
     Wikispecies
    -0.56
     Theſe
    -0.55
     Balth
    -0.54
    Chham
    -0.53
    POSITIVE LOGITS
    物的
    0.50
     vị
    0.50
    Véxase
    0.49
     Nes
    0.49
    addCriterion
    0.47
     Dr
    0.47
     anti
    0.47
    atorship
    0.46
     an
    0.46
     mass
    0.46
    Activations Density 2.377%

    No Known Activations