© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142411
    Prev
    Next
    INDEX
    Explanations

    evil concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    धीर
    0.39
     గు
    0.37
    ("",
    0.37
    (^
    0.36
     aigu
    0.35
    UnitPrice
    0.34
    форм
    0.34
    ApiOperation
    0.34
     期
    0.34
    ремен
    0.34
    POSITIVE LOGITS
     evil
    2.16
    悪
    1.95
     bad
    1.87
     Evil
    1.81
    evil
    1.77
    Evil
    1.77
     악
    1.73
     kötü
    1.71
    恶
    1.65
    惡
    1.63
    Activations Density 0.018%

    No Known Activations