© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198383
    Prev
    Next
    INDEX
    Explanations

    budburst, irautea, устойчи, real estate

    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_9_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
    el
    0.80
    ed
    0.77
    ت
    0.74
    at
    0.71
    ation
    0.66
    ing
    0.66
    ou
    0.62
    et
    0.61
    al
    0.61
    isert
    0.60
    POSITIVE LOGITS
    ра
    0.67
     법
    0.54
     어린이
    0.53
     부동산
    0.53
    ш
    0.53
    、（
    0.52
    უნქ
    0.52
    ेंसिल
    0.52
     უკ
    0.49
    ྥ
    0.49
    Activations Density 0.000%

    No Known Activations