© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195587
    Prev
    Next
    INDEX
    Explanations

    mentioning etc

    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_26_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
    െ
    0.39
    خوا
    0.39
    लिटी
    0.38
    ייה
    0.38
    ופה
    0.38
     لكن
    0.38
    ंगाना
    0.38
     entweder
    0.37
    unix
    0.37
     würde
    0.36
    POSITIVE LOGITS
    িনীত
    0.37
     horizons
    0.36
     Ad
    0.35
     borders
    0.34
     "***
    0.33
    ୫
    0.33
     Ap
    0.33
     Border
    0.33
     underserved
    0.33
     expressing
    0.32
    Activations Density 0.003%

    No Known Activations