© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44678
    Prev
    Next
    INDEX
    Explanations

    difference in

    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_3_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
    st
    0.87
    కు
    0.71
    ा
    0.70
    の
    0.70
    G
    0.68
    ја
    0.66
    ्ज
    0.66
    ン
    0.66
    ಲ್ಲಿ
    0.65
    ה
    0.65
    POSITIVE LOGITS
    at
    0.97
    er
    0.86
    ur
    0.82
    ر
    0.75
    ни
    0.73
    ar
    0.71
    ER
    0.70
    емых
    0.69
    il
    0.68
    ার
    0.67
    Activations Density 0.009%

    No Known Activations