© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211271
    Prev
    Next
    INDEX
    Explanations

    security system

    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_19_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
    素质
    0.47
     아니라
    0.46
     suitability
    0.46
    큥
    0.45
     谢
    0.45
     dysph
    0.45
     něco
    0.44
     አገልግሎ
    0.43
     উপযুক্ত
    0.43
     并
    0.43
    POSITIVE LOGITS
    전
    0.55
    Ꮇ
    0.54
    1
    0.52
    г
    0.52
    ه
    0.50
    С
    0.50
    تر
    0.48
     دهید
    0.48
    ك
    0.48
    К
    0.47
    Activations Density 0.000%

    No Known Activations