© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8541
    Prev
    Next
    INDEX
    Explanations

    hunter or hunting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    특별시
    2.79
     Dokter
    2.70
    $\
    2.68
    లు
    2.62
    ಲ್
    2.60
     দৈ
    2.58
    ła
    2.56
    $.\
    2.56
    iched
    2.56
    ^{*}$,
    2.56
    POSITIVE LOGITS
    is
    3.30
     kadar
    2.98
    ت
    2.93
    на
    2.93
    ة
    2.88
    犸
    2.84
    ️
    2.73
    at
    2.72
    ूप
    2.70
     τρό
    2.61
    Activations Density 0.018%

    No Known Activations