© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122858
    Prev
    Next
    INDEX
    Explanations

    Corp and Lewis

    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_3_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
    楕
    0.63
    宕
    0.61
    ar
    0.61
    anath
    0.59
    cích
    0.58
    ط
    0.57
    지
    0.57
    čně
    0.55
    arza
    0.55
    动作
    0.55
    POSITIVE LOGITS
     at
    0.79
    AS
    0.65
    ON
    0.62
    AN
    0.61
     for
    0.59
     .
    0.59
     фено
    0.59
    的感觉
    0.59
    的说
    0.58
     tại
    0.57
    Activations Density 0.001%

    No Known Activations