© 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. 122711
    Prev
    Next
    INDEX
    Explanations

    crazy, mad, glue, magic, дела

    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
    ਰ
    0.82
    has
    0.77
    হ
    0.77
    მ
    0.71
    on
    0.71
    hah
    0.70
    ਮ
    0.70
     بیک
    0.65
    되었습니다
    0.65
    uhe
    0.65
    POSITIVE LOGITS
    0.83
    ли
    0.80
    0.70
     can
    0.70
    de
    0.69
     cez
    0.66
    ى
    0.64
    ும்போது
    0.64
    ле
    0.63
    יל
    0.63
    Activations Density 0.006%

    No Known Activations