© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90332
    Prev
    Next
    INDEX
    Explanations

    mud, snow, garden, kitchen, rose

    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
    ニーズ
    0.60
    hlung
    0.58
    nın
    0.57
    зва
    0.57
    ٧
    0.56
    
    0.56
    니
    0.55
    ٢
    0.55
    ﺭ
    0.55
    ле
    0.54
    POSITIVE LOGITS
    in
    0.81
     be
    0.68
    o
    0.62
     zwią
    0.58
     drab
    0.56
    T
    0.54
     a
    0.54
    A
    0.54
     is
    0.54
    ice
    0.54
    Activations Density 0.001%

    No Known Activations