© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240183
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and programming constructs

    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_25_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
     interchangeably
    0.39
     shut
    0.39
     shutting
    0.38
     Đây
    0.38
     gender
    0.37
    鴛
    0.36
    由此
    0.36
     Gender
    0.36
     Timeline
    0.35
     simplify
    0.35
    POSITIVE LOGITS
     izango
    0.45
    浒
    0.42
    ura
    0.40
     tö
    0.39
    CEO
    0.39
    ții
    0.39
    łych
    0.39
    ジュアル
    0.39
    azze
    0.38
     पटना
    0.38
    Activations Density 0.000%

    No Known Activations