© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17254
    Prev
    Next
    INDEX
    Explanations

    declining harmful assistant 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_34_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
    propertyPath
    0.41
     schedule
    0.38
    ប្រតិ
    0.37
    冚
    0.37
     gover
    0.36
     grou
    0.36
    চ্ছ
    0.35
     StreamReader
    0.35
    әү
    0.35
     SCHEDULE
    0.35
    POSITIVE LOGITS
     संतु
    0.42
    jag
    0.41
    mented
    0.41
    苑
    0.39
    ishw
    0.38
     enumerable
    0.38
    onents
    0.38
    kat
    0.37
    dm
    0.37
    fect
    0.37
    Activations Density 0.001%

    No Known Activations