© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31571
    Prev
    Next
    INDEX
    Explanations

    go / Gou

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     nhiên
    1.05
    然
    0.65
    연
    0.65
     연료
    0.60
     fuel
    0.57
    燃料
    0.54
    Fuel
    0.49
     Yeon
    0.47
    fuel
    0.46
    FUEL
    0.45
    POSITIVE LOGITS
     تنگ
    0.41
    ланды
    0.41
    Pittsburgh
    0.40
    ｊ
    0.39
    ोगे
    0.38
     dott
    0.38
     باقي
    0.38
     rumours
    0.37
    ujjati
    0.37
    鸹
    0.37
    Activations Density 0.000%

    No Known Activations