© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15053
    Prev
    Next
    INDEX
    Explanations

    pornography consumption

    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_13_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
    Minimize
    0.14
    PolicyQuery
    0.14
    Mkv
    0.14
     المس
    0.14
    "，
    0.14
    t
    0.13
    Benzyl
    0.13
    쾰
    0.13
    mmmm
    0.13
    them
    0.13
    POSITIVE LOGITS
    enary
    0.15
    內的
    0.14
     likes
    0.14
     verso
    0.14
     rejection
    0.14
     unveiled
    0.13
     degli
    0.13
    ↵
    0.13
     se
    0.13
     founder
    0.13
    Activations Density 0.038%

    No Known Activations