© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58244
    Prev
    Next
    INDEX
    Explanations

    vision

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     view
    0.98
    ن
    0.89
    view
    0.74
    น
    0.73
     View
    0.67
    न
    0.62
    н
    0.61
    n
    0.58
     VIEW
    0.55
     न
    0.52
    POSITIVE LOGITS
     نظ
    1.46
     vu
    1.44
     Vu
    1.30
    Vu
    1.23
     vzh
    1.16
    vu
    0.94
     виде
    0.90
     नजर
    0.86
     вида
    0.83
     नज़र
    0.77
    Activations Density 0.038%

    No Known Activations