© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88240
    Prev
    Next
    INDEX
    Explanations

    %APPDATA%

    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
    ut
    0.74
     of
    0.64
    多い
    0.64
    т
    0.62
     antara
    0.61
     vultures
    0.60
    ofi
    0.59
     compiled
    0.58
     ६
    0.58
     œufs
    0.58
    POSITIVE LOGITS
    to
    0.63
    ;
    0.63
     Summer
    0.58
    的分
    0.58
    に変
    0.57
    思
    0.57
    硐
    0.57
    的花
    0.56
     Stok
    0.56
     Solution
    0.55
    Activations Density 0.001%

    No Known Activations