© 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. 50973
    Prev
    Next
    INDEX
    Explanations

    dunes

    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
     (
    0.69
    ↵↵
    0.69
    0.63
     È
    0.58
     \
    0.54
    りで
    0.54
    って
    0.52
    .
    0.50
    રા
    0.50
     diagonally
    0.50
    POSITIVE LOGITS
    𝙜
    0.70
    ку
    0.68
     женой
    0.67
    ente
    0.67
    PropertySheets
    0.67
    εις
    0.66
     நாட்கள்
    0.65
    mites
    0.65
    Tarea
    0.63
    энне
    0.63
    Activations Density 0.003%

    No Known Activations