© 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. 41711
    Prev
    Next
    INDEX
    Explanations

    hairdressing brush handle

    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
    ر
    0.98
    r
    0.88
     that
    0.74
    O
    0.69
    ن
    0.68
    T
    0.64
     viel
    0.63
    D
    0.63
    that
    0.62
    G
    0.62
    POSITIVE LOGITS
    ா
    0.72
    д
    0.71
    ᱐
    0.70
    重要な
    0.67
    서
    0.64
    アー
    0.63
    ころ
    0.63
    ຄວາມ
    0.62
    govor
    0.62
    安心して
    0.61
    Activations Density 0.000%

    No Known Activations