© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124779
    Prev
    Next
    INDEX
    Explanations

    Bill of Materials (BOM)

    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
    '
    0.86
    THAN
    0.73
    К
    0.71
    COP
    0.68
    khan
    0.68
    CHRIST
    0.67
    CHEAT
    0.67
    frac
    0.66
    érieure
    0.66
    at
    0.65
    POSITIVE LOGITS
    ри
    0.79
    س
    0.79
    с
    0.75
    น
    0.72
     it
    0.72
    de
    0.68
     orchestration
    0.66
     percobaan
    0.64
    리
    0.64
    та
    0.64
    Activations Density 0.000%

    No Known Activations