© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46044
    Prev
    Next
    INDEX
    Explanations

    don't worry or don't miss

    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_13_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
    _)
    0.54
    슨
    0.54
    ش
    0.53
     delineate
    0.52
    SON
    0.52
    )。
    0.50
     अथवा
    0.49
    سون
    0.49
    ór
    0.49
     ufficial
    0.49
    POSITIVE LOGITS
     rozwiąz
    0.53
     náklady
    0.48
     폐
    0.46
     hype
    0.46
     goo
    0.45
    ปัญหา
    0.45
    ౪
    0.44
     İstanbul
    0.44
    mniejs
    0.44
    폐
    0.43
    Activations Density 0.009%

    No Known Activations