© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37585
    Prev
    Next
    INDEX
    Explanations

    rib cage and Rio Grande

    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
     i
    0.91
    ם
    0.86
    ING
    0.86
     e
    0.76
     a
    0.73
     đúng
    0.72
     chez
    0.71
     tempi
    0.70
     și
    0.69
    >$
    0.69
    POSITIVE LOGITS
    t
    0.94
    in
    0.84
    al
    0.84
    ic
    0.79
    ar
    0.79
    an
    0.75
    ik
    0.73
    h
    0.72
    impose
    0.69
    ان
    0.66
    Activations Density 0.001%

    No Known Activations