© 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. 139396
    Prev
    Next
    INDEX
    Explanations

    **bin** followed by file, ance, ning, or ocular

    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
    ोज
    0.49
     Binary
    0.40
    Binary
    0.37
     bibendum
    0.37
    NUM
    0.37
    졸
    0.37
     binh
    0.36
    Not
    0.36
    廢
    0.36
    ⵄ
    0.36
    POSITIVE LOGITS
     параметр
    0.39
     Melrose
    0.39
     permutation
    0.38
     Bookmark
    0.37
    يجي
    0.37
     pdf
    0.36
    ោះ
    0.36
    kte
    0.35
    ঙ্গা
    0.35
    erto
    0.35
    Activations Density 0.001%

    No Known Activations