© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4656
    Prev
    Next
    INDEX
    Explanations

    Ying, Young, 영, 英, īng

    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_38_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
    rakk
    0.40
     waxed
    0.37
    يطان
    0.36
    HN
    0.36
    锡
    0.35
    mRNA
    0.35
     আসলে
    0.34
     아마
    0.34
    mnf
    0.34
     Въ
    0.34
    POSITIVE LOGITS
    EnglishMarks
    0.36
    نګ
    0.35
    zA
    0.35
     угро
    0.35
     الشه
    0.35
    盈
    0.35
     influences
    0.34
     SHALL
    0.34
    繕
    0.34
    ชี
    0.33
    Activations Density 0.014%

    No Known Activations