© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213449
    Prev
    Next
    INDEX
    Explanations

    Violent

    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_50_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
    ريخ
    0.41
    Pom
    0.41
     Pom
    0.40
    パーカー
    0.39
    ptic
    0.38
     দিবার
    0.38
     පා
    0.38
    琯
    0.38
     idi
    0.38
     каждо
    0.38
    POSITIVE LOGITS
    Viol
    1.87
     viol
    1.79
     Viol
    1.68
    viol
    1.62
     vio
    1.52
     Violent
    1.34
     violet
    1.32
     VI
    1.31
    violent
    1.30
     violent
    1.29
    Activations Density 0.002%

    No Known Activations