© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40431
    Prev
    Next
    INDEX
    Explanations

    <end_of_turn>

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    נע
    0.41
     आयुष्मान
    0.41
     ຄ
    0.37
    ഃ
    0.36
    कु
    0.36
    andran
    0.36
     nghỉ
    0.35
    ホイール
    0.35
    :‏
    0.35
    ⬯
    0.35
    POSITIVE LOGITS
    brown
    0.40
    resc
    0.37
     Henson
    0.37
    Brow
    0.36
    rir
    0.36
    lens
    0.36
    itz
    0.36
     આપ
    0.36
     flesh
    0.36
    痨
    0.36
    Activations Density 0.006%

    No Known Activations