© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10008
    Prev
    Next
    INDEX
    Explanations

    text about the game World of Warcraft, specifically healing and character builds

    oai_token-act-pair · gemini-2.0-flash

    video games/software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     '{@
    -0.73
    WithMany
    -0.67
     مرئيه
    -0.60
    ighorn
    -0.59
     Wikimedijinoj
    -0.59
     الاطلاع
    -0.56
    новниш
    -0.56
    جغرافيا
    -0.55
    kola
    -0.54
    <tfoot>
    -0.53
    POSITIVE LOGITS
     الحره
    0.56
    CppCodeGen
    0.50
     BitmapFactory
    0.48
    RectangleBorder
    0.48
    GetAxis
    0.47
    RenderAtEndOf
    0.46
     itinéraires
    0.45
    protoimpl
    0.45
     Tears
    0.45
    TextUtils
    0.45
    Activations Density 2.308%

    No Known Activations