© 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. 38892
    Prev
    Next
    INDEX
    Explanations

    index_col, column mapping

    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
    ä
    0.96
    st
    0.85
    ن
    0.78
    R
    0.74
    تر
    0.73
    sh
    0.71
    å
    0.71
    stå
    0.71
    1
    0.71
    ре
    0.70
    POSITIVE LOGITS
    ில்
    0.71
    اك
    0.69
     diritto
    0.66
     دين
    0.66
     جوړونکی
    0.66
    钣
    0.62
     Сак
    0.61
     conceivably
    0.61
    '>"
    0.61
     ينا
    0.61
    Activations Density 0.002%

    No Known Activations