© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143507
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

    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_0_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
    ي
    1.66
    কে
    1.47
     for
    1.46
     in
    1.41
    ب
    1.36
    i
    1.33
    ج
    1.33
    ad
    1.28
    지
    1.27
    ر
    1.26
    POSITIVE LOGITS
    یکه
    0.78
    세요
    0.73
    、《
    0.73
    ンの
    0.72
    리티
    0.72
    死的
    0.71
    되며
    0.70
    ală
    0.69
    ⅽ
    0.69
    らず
    0.68
    Activations Density 0.499%

    No Known Activations