© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242873
    Prev
    Next
    INDEX
    Explanations

    promote, facilitate, or enable 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_40_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
    targets
    0.40
     hơi
    0.39
     ぐらい
    0.38
     ಸ್ವಲ್ಪ
    0.37
     Nomenclature
    0.36
    uck
    0.36
    iksi
    0.36
    徹
    0.35
    ysh
    0.34
     targets
    0.34
    POSITIVE LOGITS
     crime
    1.27
     crimes
    1.16
    crime
    1.14
    Crime
    1.08
     Crimes
    1.03
     Crime
    0.98
    犯罪
    0.88
     अपराध
    0.86
     crimen
    0.84
     преступ
    0.80
    Activations Density 0.007%

    No Known Activations