© 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. 79969
    Prev
    Next
    INDEX
    Explanations

    code completion

    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
     _,
    0.49
    _,
    0.40
     vě
    0.39
     टेंस
    0.39
     До
    0.39
    %,
    0.39
    となり
    0.39
     facteur
    0.39
     रा
    0.38
     ਦ
    0.38
    POSITIVE LOGITS
    Â
    0.48
    ת
    0.38
    hanahu
    0.38
    unehmen
    0.37
    ^{-/-}$
    0.37
     সাধারন
    0.36
    console
    0.36
    нинград
    0.36
    ẫn
    0.35
    simulation
    0.35
    Activations Density 0.000%

    No Known Activations