© 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. 28571
    Prev
    Next
    INDEX
    Explanations

    incitement to hatred

    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
    Ink
    0.42
     प्रोटे
    0.42
     ပဲ
    0.41
     против
    0.38
     arqu
    0.38
    墨
    0.38
     इंट्रो
    0.38
     juara
    0.37
     hak
    0.37
    Anti
    0.37
    POSITIVE LOGITS
     ઘટના
    0.48
     ঘটনা
    0.43
     physical
    0.43
     macroscopic
    0.40
     घटनाएं
    0.38
     물리
    0.38
     scanner
    0.37
    Ậ
    0.37
     Nxe
    0.37
    事件
    0.37
    Activations Density 0.003%

    No Known Activations