© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195052
    Prev
    Next
    INDEX
    Explanations

    rot

    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_15_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
    文物
    0.54
    турой
    0.53
    man
    0.49
     Photographs
    0.48
     Moderne
    0.48
     沒有
    0.48
    icida
    0.48
    
    0.47
    сны
    0.47
     உயர்த்த
    0.47
    POSITIVE LOGITS
     accru
    0.55
     basins
    0.55
    Along
    0.53
    Event
    0.53
     eddies
    0.53
     semantic
    0.52
    Throttle
    0.52
    *
    0.50
     quantum
    0.50
    പ്പെട്ടു
    0.50
    Activations Density 0.001%

    No Known Activations