© 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. 38941
    Prev
    Next
    INDEX
    Explanations

    850

    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
     دلیل
    0.79
    ７
    0.75
     быть
    0.71
    ᱘
    0.71
     канторы
    0.69
    ᱙
    0.68
    ᱗
    0.68
     reinstall
    0.68
     видели
    0.67
    ്
    0.67
    POSITIVE LOGITS
     (
    0.96
    ul
    0.84
    ك
    0.83
    un
    0.82
    im
    0.82
    ina
    0.81
    ala
    0.79
    ac
    0.78
    us
    0.78
    ks
    0.77
    Activations Density 0.002%

    No Known Activations