© 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. 133763
    Prev
    Next
    INDEX
    Explanations

    methods and their usage

    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
    з
    0.99
    น
    0.89
    ्या
    0.84
     мы
    0.75
     производи
    0.73
     Фе
    0.73
    ).
    0.72
     `:`,
    0.72
    ся
    0.72
     Ар
    0.72
    POSITIVE LOGITS
    i
    1.54
    um
    1.27
    ي
    1.15
    in
    1.11
    و
    1.10
    e
    1.09
    ו
    1.04
    at
    1.03
    ে
    0.97
    のは
    0.96
    Activations Density 0.010%

    No Known Activations