© 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. 45511
    Prev
    Next
    INDEX
    Explanations

    authentication and authorization

    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
    In
    0.77
    おお
    0.74
    ו
    0.74
    Magnitude
    0.73
    Inflation
    0.71
    Change
    0.70
    Not
    0.69
    カス
    0.69
    Question
    0.69
    Input
    0.68
    POSITIVE LOGITS
    :
    0.74
    ag
    0.71
    ål
    0.67
     tinha
    0.65
     रवाना
    0.64
     então
    0.63
     besten
    0.62
     त्यांच्या
    0.61
     steered
    0.61
     baix
    0.60
    Activations Density 0.009%

    No Known Activations