© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54205
    Prev
    Next
    INDEX
    Explanations

    wasn't... or a

    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_30_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
     và
    0.56
     ਅਤੇ
    0.56
     һәм
    0.55
     și
    0.54
    ແລະ
    0.54
     və
    0.52
    และ
    0.51
     и
    0.49
     మరియు
    0.48
     և
    0.48
    POSITIVE LOGITS
     Clearing
    0.37
     Scud
    0.37
    ኾ
    0.37
    ･･･
    0.36
     countless
    0.36
     Victor
    0.36
    σε
    0.36
    خن
    0.36
     infine
    0.35
     whichever
    0.35
    Activations Density 0.003%

    No Known Activations