© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134548
    Prev
    Next
    INDEX
    Explanations

    urls ending in file extensions

    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_6_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
    ر
    1.06
    The
    0.91
    ب
    0.88
     I
    0.82
    iaan
    0.78
    0.77
     üks
    0.76
     "
    0.75
    أت
    0.75
    Cuando
    0.73
    POSITIVE LOGITS
    ни
    1.23
    p
    1.03
    س
    0.87
    с
    0.85
    স
    0.82
    ma
    0.82
    al
    0.80
    panelMenuList
    0.79
    kenalkan
    0.77
    kan
    0.77
    Activations Density 0.001%

    No Known Activations