© 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. 34661
    Prev
    Next
    INDEX
    Explanations

    bre, bres, ball, etable patterns

    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
     druk
    0.70
     on
    0.68
    ě
    0.68
     допол
    0.67
     acquaintance
    0.67
     appré
    0.66
     ação
    0.63
     an
    0.63
     underground
    0.63
     jeopard
    0.62
    POSITIVE LOGITS
    rotated
    0.88
    were
    0.80
    کنندگان
    0.75
    밂
    0.71
    wString
    0.70
    ها
    0.67
    as
    0.66
    ids
    0.66
    вся
    0.65
    textured
    0.65
    Activations Density 0.001%

    No Known Activations