© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202801
    Prev
    Next
    INDEX
    Explanations

    script tags

    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_12_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
    WITH
    0.61
    缪
    0.59
     with
    0.57
     ইরা
    0.55
     Flora
    0.52
    बॉलीवुड
    0.52
     WITH
    0.50
    with
    0.50
     guna
    0.49
     executors
    0.48
    POSITIVE LOGITS
    ו
    0.67
    و
    0.59
    𝐨
    0.54
    o
    0.54
    ز
    0.53
    وْ
    0.52
    eti
    0.52
    ̈
    0.52
    oliberal
    0.51
    CATS
    0.51
    Activations Density 0.000%

    No Known Activations