© 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. 89528
    Prev
    Next
    INDEX
    Explanations

    refusal to generate erotic 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
    ↵
    0.67
    nt
    0.54
    .
    0.54
    *
    0.54
     awards
    0.52
     milestones
    0.52
     Sci
    0.51
     award
    0.51
    +
    0.51
    ’
    0.51
    POSITIVE LOGITS
    کروچ
    0.61
    EnglishMarks
    0.60
     التجارية
    0.57
     व्यापार
    0.55
    يي
    0.54
    BetMap
    0.53
     واست
    0.53
    empres
    0.53
    বিহার
    0.52
     bestimmten
    0.52
    Activations Density 0.004%

    No Known Activations