© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92501
    Prev
    Next
    INDEX
    Explanations

    refuses harmful requests

    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_60_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
    ↵↵
    0.93
     时尚
    0.62
    ↵↵↵
    0.60
     红
    0.59
     热
    0.55
     马
    0.54
     与
    0.54
     专业
    0.54
     过
    0.52
     爱
    0.52
    POSITIVE LOGITS
    0.63
    *
    0.60
    For
    0.55
    Here
    0.52
    You
    0.51
    This
    0.50
    برای
    0.50
        
    0.50
    Let
    0.50
    ```
    0.49
    Activations Density 0.056%

    No Known Activations