© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3597
    Prev
    Next
    INDEX
    Explanations

    mentions of trades and basketball players

    oai_token-act-pair · gemini-2.0-flash

    non-English phrases or specialized terms

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

    foreign words

    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
     consultez
    -0.50
    зайн
    -0.47
    zeptember
    -0.47
     Erl
    -0.46
    aarrggbb
    -0.46
     PARSER
    -0.46
     engraçadas
    -0.46
    )__
    -0.45
    arshan
    -0.45
    apimachinery
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.71
     bezeichneter
    0.70
    Diweddarwch
    0.65
    RenderAtEndOf
    0.65
    OGND
    0.61
    Искәрмәләр
    0.56
    Vidite
    0.52
    orace
    0.52
    userdetails
    0.50
    tvguidetime
    0.50
    Activations Density 0.321%

    No Known Activations