© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176485
    Prev
    Next
    INDEX
    Explanations

    you print or write

    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_20_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
     ثانوي
    0.48
     runga
    0.48
     empez
    0.45
     afric
    0.45
     ஸ்ரீ
    0.43
     academically
    0.43
    愀
    0.43
    有り
    0.42
     एक्सेल
    0.41
    偶然
    0.41
    POSITIVE LOGITS
     kiểu
    0.40
    বিহীন
    0.40
    typeface
    0.40
     χρώ
    0.40
    ский
    0.39
    ]{
    0.39
    仇
    0.39
     bảo
    0.38
    ಗೊಳ
    0.38
     Poké
    0.38
    Activations Density 0.000%

    No Known Activations