© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50741
    Prev
    Next
    INDEX
    Explanations

    Osaka

    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_10_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
    ä
    0.57
    o
    0.54
    A
    0.54
    on
    0.53
    an
    0.53
    ب
    0.52
    }
    0.49
    *
    0.48
    ন
    0.48
    c
    0.47
    POSITIVE LOGITS
     Б
    0.47
     Чу
    0.45
     yearn
    0.45
    ТС
    0.43
    СТЬ
    0.42
     Ф
    0.41
    兵庫
    0.41
     considere
    0.40
     Мето
    0.40
     നിര
    0.40
    Activations Density 0.011%

    No Known Activations