© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46058
    Prev
    Next
    INDEX
    Explanations

    genshin impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    _$
    0.73
    $
    0.71
    _
    0.68
    ম
    0.67
    та
    0.66
    ור
    0.65
    $>
    0.64
    ।
    0.64
    は
    0.64
    *
    0.63
    POSITIVE LOGITS
    ível
    0.63
     véritable
    0.55
     Exec
    0.54
     прогноз
    0.54
     suggestion
    0.53
     விழு
    0.53
    ramatta
    0.52
    "));
    0.52
     execut
    0.52
     executes
    0.51
    Activations Density 0.002%

    No Known Activations