© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81869
    Prev
    Next
    INDEX
    Explanations

    Kopf

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     計
    0.42
    änä
    0.39
    otte
    0.39
     zat
    0.38
    ровке
    0.38
     สา
    0.38
    gqlgen
    0.37
     главное
    0.37
    罣
    0.37
    olverine
    0.37
    POSITIVE LOGITS
     Kop
    1.42
     Kö
    1.32
     kop
    1.29
     Kopp
    1.18
    Kö
    1.15
    Cop
    1.14
     Cop
    1.13
     COP
    1.10
     كوب
    1.09
     коп
    1.09
    Activations Density 0.000%

    No Known Activations