© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196575
    Prev
    Next
    INDEX
    Explanations

    Appendix A, sports, playing

    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_9_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
    ﺭ
    0.48
    リンク
    0.45
    غيل
    0.45
    ﺱ
    0.44
    িসে
    0.43
    servlet
    0.43
     सि
    0.42
    ﻬ
    0.42
     мили
    0.41
    سي
    0.40
    POSITIVE LOGITS
    an
    0.58
    é
    0.57
    ång
    0.54
     acrobat
    0.52
    ik
    0.52
    电力
    0.50
    ide
    0.47
     alla
    0.46
     deformations
    0.46
    ocyst
    0.46
    Activations Density 0.000%

    No Known Activations