© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79917
    Prev
    Next
    INDEX
    Explanations

    Mick Taylor, merc antonyms

    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_0_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
    с
    2.14
    و
    2.11
    다
    1.96
    ו
    1.88
    ні
    1.87
    на
    1.75
    س
    1.73
    2
    1.63
     can
    1.62
    the
    1.62
    POSITIVE LOGITS
    t
    1.60
     on
    1.33
    ０
    1.22
     אז
    1.18
     renormal
    1.17
     возможности
    1.13
    b
    1.13
    ﺭ
    1.13
    ۰۰
    1.12
    のリ
    1.11
    Activations Density 0.000%

    No Known Activations