© 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. 17559
    Prev
    Next
    INDEX
    Explanations

    protection from danger or harm

    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
    activeIndex
    0.42
    㯎
    0.40
    建議
    0.39
    Resizable
    0.38
    Equal
    0.38
    价值
    0.37
    ंख
    0.37
    带
    0.37
     tumbled
    0.36
    valu
    0.36
    POSITIVE LOGITS
     spared
    0.79
     shield
    0.73
     protection
    0.66
     tránh
    0.61
    避免
    0.61
     avoid
    0.60
    protection
    0.60
     protected
    0.59
     Protection
    0.59
     exempted
    0.59
    Activations Density 0.078%

    No Known Activations