© 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. 29623
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ны
    0.70
    t
    0.69
    ست
    0.68
    ри
    0.66
    ми
    0.64
    рен
    0.63
    ти
    0.63
    ки
    0.62
    циа
    0.62
    нг
    0.62
    POSITIVE LOGITS
    <()>
    0.64
     anteced
    0.61
     വര്‍
    0.61
    ?
    0.61
     auspicious
    0.60
    絣
    0.59
     அதிகரி
    0.59
     ผ้า
    0.59
     ܘ
    0.57
     litro
    0.57
    Activations Density 0.000%

    No Known Activations