© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199878
    Prev
    Next
    INDEX
    Explanations

    proactive

    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_12_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
    โม
    0.52
    옇
    0.50
     programación
    0.50
    ﺸ
    0.50
     dimensión
    0.49
    HIG
    0.49
     interplay
    0.49
    塑造
    0.48
    ஷ
    0.48
     sharpness
    0.48
    POSITIVE LOGITS
    are
    0.62
    It
    0.59
    Ia
    0.58
     Ilya
    0.57
    寯
    0.55
    Soil
    0.55
     OAuth
    0.54
    bride
    0.54
    ('=
    0.54
    婕
    0.54
    Activations Density 0.001%

    No Known Activations