© 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. 34696
    Prev
    Next
    INDEX
    Explanations

    PR defines Vote, Reference

    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
    ز
    0.69
    ри
    0.69
    स
    0.65
    し
    0.63
     शेट्टी
    0.61
     kama
    0.59
    с
    0.59
     Okamoto
    0.58
    จ
    0.57
    வுக
    0.57
    POSITIVE LOGITS
    tan
    0.70
    té
    0.66
    を起こ
    0.64
    t
    0.63
    an
    0.62
    ان
    0.59
    во
    0.57
    urup
    0.57
    stechnik
    0.57
    LEC
    0.56
    Activations Density 0.008%

    No Known Activations