© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45097
    Prev
    Next
    INDEX
    Explanations

    criminal history and violations

    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_22_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
     mutations
    0.34
    テスト
    0.32
     Mutation
    0.31
     Mutations
    0.31
    Ｍ
    0.30
    test
    0.30
    Test
    0.30
     test
    0.29
    基本
    0.29
     ம
    0.29
    POSITIVE LOGITS
     criminal
    0.37
     taw
    0.37
     infractions
    0.36
     schol
    0.36
     alcohol
    0.34
     гражда
    0.34
     ассоциа
    0.34
    asche
    0.33
    gamb
    0.33
    attro
    0.33
    Activations Density 0.034%

    No Known Activations