© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7085
    Prev
    Next
    INDEX
    Explanations

    refusal to harmful requests

    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_39_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
    brun
    0.38
    Brun
    0.38
    Sau
    0.38
    Tum
    0.36
    }_{+}
    0.36
     tum
    0.36
     brun
    0.36
     bla
    0.35
    trailing
    0.35
    ドラ
    0.35
    POSITIVE LOGITS
     what
    0.52
    what
    0.48
     WHAT
    0.48
     آنچه
    0.47
    สิ่งที่
    0.43
     何
    0.42
     ceea
    0.41
     What
    0.41
    WHAT
    0.40
     Unser
    0.39
    Activations Density 0.263%

    No Known Activations