© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26388
    Prev
    Next
    INDEX
    Explanations

    udemy or udacity

    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_10_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
    ↵
    0.75
    :
    0.68
    ;
    0.65
     газе
    0.61
     видимо
    0.59
     postulated
    0.58
     бес
    0.57
     посред
    0.57
     пробе
    0.57
    ми
    0.56
    POSITIVE LOGITS
    0.78
    。
    0.71
    W
    0.65
    會
    0.63
    shear
    0.62
    有所
    0.59
    م
    0.58
    cos
    0.57
    孙
    0.57
    Russia
    0.57
    Activations Density 0.003%

    No Known Activations