© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16180
    Prev
    Next
    INDEX
    Explanations

    danger and harm to self

    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_40_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
    以及
    0.43
    などの
    0.42
    以外
    0.41
    그리고
    0.40
    および
    0.40
     および
    0.40
    ือน
    0.39
     및
    0.38
     AND
    0.38
     naro
    0.38
    POSITIVE LOGITS
     both
    2.38
    both
    2.22
     både
    2.05
    Both
    1.90
     zowel
    1.90
     sowohl
    1.88
     zarówno
    1.88
     Both
    1.86
     cả
    1.82
    ทั้ง
    1.78
    Activations Density 0.306%

    No Known Activations