© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    mentions of an athlete, especially their accomplishments in a competition

    oai_token-act-pair · gemini-2.0-flash

    unique or specialized terminology

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

    random text

    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
    AccessorTable
    -0.60
    stateProvider
    -0.57
     propOrder
    -0.54
     ſch
    -0.50
     AssemblyTitle
    -0.49
     ſol
    -0.49
    OrBuilder
    -0.49
     Eſ
    -0.49
     verſ
    -0.47
     Chwiliwch
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.68
    anglès
    0.60
    RectangleBorder
    0.57
    ADVERTISEMENT
    0.57
     Baillargeon
    0.57
     bag
    0.55
    __;
    0.54
    enumii
    0.54
     pomen
    0.53
    aryana
    0.52
    Activations Density 0.394%

    No Known Activations