© 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. 39467
    Prev
    Next
    INDEX
    Explanations

    en cas de

    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
    squiggle
    0.78
    ના
    0.72
    (",
    0.70
    AIR
    0.69
    ’
    0.69
    在
    0.69
    2
    0.68
    なった
    0.68
    なって
    0.67
    Reuse
    0.66
    POSITIVE LOGITS
     on
    0.77
    да
    0.75
    ó
    0.75
     graced
    0.73
     of
    0.66
    ató
    0.66
    лю
    0.66
     entrusted
    0.65
     remedied
    0.65
     autorisé
    0.64
    Activations Density 0.003%

    No Known Activations