© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58329
    Prev
    Next
    INDEX
    Explanations

    visual question answering

    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_11_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
     电
    0.59
    ReadFile
    0.50
    разуме
    0.50
     كهرب
    0.50
    പം
    0.47
    ='.
    0.47
    晝
    0.45
    宿
    0.45
    隸
    0.45
    RIBUTES
    0.45
    POSITIVE LOGITS
     e
    0.63
    by
    0.63
    awsze
    0.57
     möjlig
    0.56
     Hog
    0.56
     Jensen
    0.56
     aynı
    0.55
    ovat
    0.55
    भारतीय
    0.54
     Julie
    0.54
    Activations Density 0.005%

    No Known Activations