© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143202
    Prev
    Next
    INDEX
    Explanations

    such as, etc

    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_0_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
    2
    1.49
    $,
    1.34
    $.
    1.25
    ların
    1.21
    ка
    1.17
    ;
    1.13
    rie
    1.04
    ne
    1.03
    stelle
    1.02
    一个小
    1.02
    POSITIVE LOGITS
    ت
    1.63
    ли
    1.54
    고
    1.52
    ின்
    1.51
    is
    1.50
    る
    1.49
    '
    1.40
    ри
    1.37
     divulg
    1.35
    ak
    1.34
    Activations Density 0.000%

    No Known Activations