© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33925
    Prev
    Next
    INDEX
    Explanations

    build upon

    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
     monopolist
    0.70
    le
    0.67
     guten
    0.67
    ت
    0.67
     $
    0.66
     legenda
    0.66
     faker
    0.66
    ing
    0.64
     I
    0.63
     JP
    0.62
    POSITIVE LOGITS
    ↵↵
    0.75
    टाइम
    0.69
    Y
    0.68
    かかる
    0.67
    समय
    0.63
    U
    0.63
    지만
    0.62
    的時間
    0.61
     δυνατό
    0.61
     साल
    0.60
    Activations Density 0.049%

    No Known Activations