© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194785
    Prev
    Next
    INDEX
    Explanations

    torture

    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
    飞机
    0.48
     Wicklow
    0.48
    腳
    0.48
     Sehen
    0.46
    可以通过
    0.45
    是一個
    0.44
     UILabel
    0.44
    ем
    0.43
    潮
    0.43
    可以使用
    0.43
    POSITIVE LOGITS
     streetwear
    0.53
    ਹੁ
    0.53
    мма
    0.52
     webpages
    0.50
     infot
    0.50
     ornament
    0.49
     apps
    0.49
    iquette
    0.48
     flancs
    0.48
    agonal
    0.48
    Activations Density 0.002%

    No Known Activations