© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80746
    Prev
    Next
    INDEX
    Explanations

    without

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     ნახ
    0.41
    ektir
    0.39
    異なる
    0.39
    >>>>>>>>
    0.38
    ეგი
    0.37
     இம்ம
    0.37
    ЗА
    0.37
    ﻳ
    0.36
    ﺳ
    0.36
    يمي
    0.36
    POSITIVE LOGITS
     without
    0.88
     ohne
    0.78
    without
    0.73
     без
    0.73
     tanpa
    0.72
     Without
    0.71
     senza
    0.70
     zonder
    0.68
     बिना
    0.67
     fără
    0.66
    Activations Density 0.001%

    No Known Activations