© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    violence, illegal acts, or harm

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     transgression
    0.41
     béton
    0.38
    风险
    0.37
     disqual
    0.37
     disqualify
    0.36
     wrongdoing
    0.35
     yanlış
    0.34
    ዝና
    0.34
    Healing
    0.33
    [*][[
    0.33
    POSITIVE LOGITS
     facilitation
    0.40
     Encour
    0.39
     encouraging
    0.38
     Facilit
    0.38
     MUR
    0.38
     soliciting
    0.36
     bou
    0.36
     encourage
    0.35
     solic
    0.35
     encouragement
    0.35
    Activations Density 0.420%

    No Known Activations