© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164361
    Prev
    Next
    INDEX
    Explanations

    regex considerations

    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_31_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
    Desen
    0.38
    秒
    0.37
     మొత్త
    0.37
     прав
    0.37
    月份
    0.36
    ডিট
    0.36
    DateTimeField
    0.36
     ಒಳ್ಳೆಯ
    0.36
    PTION
    0.35
    语句
    0.34
    POSITIVE LOGITS
     berbagi
    0.42
     گرم
    0.40
    𝗎
    0.40
    ostrum
    0.40
    asty
    0.39
     সম্মুখে
    0.39
    azón
    0.38
     cock
    0.38
     comun
    0.38
    wärm
    0.38
    Activations Density 0.012%

    No Known Activations