© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138981
    Prev
    Next
    INDEX
    Explanations

    quotations and quotes

    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_37_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
    issionais
    0.41
     ኩ
    0.40
     solic
    0.38
    操作
    0.37
    大赛
    0.37
     message
    0.37
    station
    0.37
     perdu
    0.37
    王朝
    0.37
     zaw
    0.36
    POSITIVE LOGITS
    aturas
    0.40
     তোলেন
    0.39
     Antip
    0.38
    חק
    0.38
    觟
    0.38
     quoting
    0.37
     spoiling
    0.37
     natur
    0.37
     exposing
    0.37
    Quote
    0.37
    Activations Density 0.002%

    No Known Activations