© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36316
    Prev
    Next
    INDEX
    Explanations

    sexually explicit content

    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
    ᱒
    0.69
    ే
    0.59
     čo
    0.58
    ᱕
    0.57
    ۴
    0.56
    2
    0.54
    ３
    0.54
    
    0.54
     což
    0.53
    ٢
    0.52
    POSITIVE LOGITS
     pornography
    0.50
     Jawah
    0.50
     retard
    0.49
     tungsten
    0.49
    E
    0.48
     E
    0.48
     ईंधन
    0.48
    ContextHeader
    0.47
     transmittance
    0.47
    BeerItem
    0.47
    Activations Density 0.096%

    No Known Activations