© 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. 41249
    Prev
    Next
    INDEX
    Explanations

    stock picking, Android, images, syndrome

    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
    '
    0.91
    ’
    0.86
    \
    0.67
     shovel
    0.62
     său
    0.59
     olds
    0.58
     iron
    0.58
     cranial
    0.57
     ancien
    0.57
    $',
    0.57
    POSITIVE LOGITS
    at
    0.77
     स्टॉक
    0.71
     الرئيس
    0.61
    id
    0.60
    entityManager
    0.59
    не
    0.58
    can
    0.58
    os
    0.57
    از
    0.57
    éviter
    0.57
    Activations Density 0.003%

    No Known Activations