© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181693
    Prev
    Next
    INDEX
    Explanations

    graph traversal algorithms

    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_29_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
    であれば
    0.39
     Leveraging
    0.37
     exhibiting
    0.37
     "|"
    0.37
     nearing
    0.37
    展
    0.36
    педи
    0.35
    _,
    0.34
     حنا
    0.34
     WINTER
    0.34
    POSITIVE LOGITS
    CHECKS
    0.37
     Lancaster
    0.36
     ప్రకట
    0.36
     terbuka
    0.35
    宮
    0.35
    অনু
    0.34
     分析
    0.34
     regretted
    0.33
    给自己
    0.33
     অতীতের
    0.33
    Activations Density 0.002%

    No Known Activations