© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196115
    Prev
    Next
    INDEX
    Explanations

    torture, interrogation, 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_15_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
    enf
    0.53
    Underwater
    0.51
    눅
    0.50
    rijven
    0.49
     Система
    0.48
    マ
    0.48
    си
    0.47
    İ
    0.47
    Winter
    0.46
    Ŭ
    0.46
    POSITIVE LOGITS
     prostit
    0.50
    чины
    0.47
     M
    0.46
     Actual
    0.46
     Willing
    0.46
     patrón
    0.45
    pattern
    0.45
     ভা
    0.45
     Tate
    0.45
     Tại
    0.45
    Activations Density 0.000%

    No Known Activations