© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173198
    Prev
    Next
    INDEX
    Explanations

    doodle, gar, ige, ol, one

    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
     ແລະ
    0.42
    pr
    0.42
    偕
    0.41
    zas
    0.40
    ylmethylsulfanyl
    0.39
    anns
    0.39
     Milli
    0.39
    व्स
    0.39
     Terri
    0.39
    ds
    0.38
    POSITIVE LOGITS
     electronic
    0.52
     clogging
    0.50
     clogged
    0.49
    殭
    0.46
     হয়
    0.46
    Electronic
    0.45
     الالكتر
    0.45
     biodiesel
    0.45
     alternation
    0.45
     crossings
    0.45
    Activations Density 0.000%

    No Known Activations