© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87349
    Prev
    Next
    INDEX
    Explanations

    mix of uppercase letters, lowercase letters, and numbers

    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_23_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
    <unused21>
    0.42
     रियलिटी
    0.37
     realtà
    0.37
    쌤
    0.36
    vers
    0.36
     outwards
    0.34
    ors
    0.34
    mers
    0.34
    अधिक
    0.34
     Beverages
    0.34
    POSITIVE LOGITS
     화
    0.44
     ни
    0.42
     refuted
    0.41
     оки
    0.40
    ']]
    0.40
     ци
    0.39
    cısı
    0.39
     Scrolling
    0.39
    嘊
    0.38
    STRO
    0.38
    Activations Density 0.002%

    No Known Activations