© 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. 145819
    Prev
    Next
    INDEX
    Explanations

    GMP compliance and heartburn

    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
    I
    1.61
    ک
    1.60
    ו
    1.58
    те
    1.54
    M
    1.52
    ти
    1.48
    W
    1.45
    ب
    1.44
    ס
    1.44
     grupos
    1.43
    POSITIVE LOGITS
     are
    1.29
    ra
    1.25
    手
    1.06
    ia
    1.03
    ó
    0.99
     indenture
    0.96
    ín
    0.96
    st
    0.95
    ০
    0.94
    䏌
    0.93
    Activations Density 0.000%

    No Known Activations