© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16940
    Prev
    Next
    INDEX
    Explanations

    violence, control, abuse

    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
     hoạt
    0.39
    पं
    0.37
     misdemeanor
    0.34
    ዳ
    0.33
     revoc
    0.33
    Carn
    0.32
     सहानुभूति
    0.32
     活动
    0.31
    NAR
    0.31
    师
    0.31
    POSITIVE LOGITS
     violencia
    0.42
     violence
    0.41
     violência
    0.41
    violence
    0.39
     Mé
    0.36
     Violence
    0.35
     bf
    0.35
    ೩
    0.35
    \}_{
    0.34
    SwingConstants
    0.34
    Activations Density 0.038%

    No Known Activations