© 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. 38731
    Prev
    Next
    INDEX
    Explanations

    module structure and installation

    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
    จะ
    0.93
    是
    0.77
    ት
    0.75
    ing
    0.74
    text
    0.74
    ä
    0.72
    A
    0.71
    ை
    0.70
    l
    0.69
    కు
    0.68
    POSITIVE LOGITS
     불구하고
    0.68
    :
    0.63
    orer
    0.57
     числа
    0.57
     разнообраз
    0.55
    irs
    0.55
     credible
    0.55
    ^{*
    0.55
     burs
    0.54
    >(</
    0.54
    Activations Density 0.000%

    No Known Activations