© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104228
    Prev
    Next
    INDEX
    Explanations

    contaminants, taut

    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_1_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
    -
    1.33
    _
    1.20
    ти
    1.11
    る
    1.09
    );
    0.95
    |(
    0.95
    el
    0.94
    5
    0.88
    4
    0.88
    ,【
    0.86
    POSITIVE LOGITS
    ні
    1.19
    ك
    1.02
    ных
    0.98
    न
    0.98
     that
    0.96
     mágico
    0.93
    ка
    0.91
     in
    0.87
    在
    0.86
    that
    0.86
    Activations Density 0.000%

    No Known Activations