© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36803
    Prev
    Next
    INDEX
    Explanations

    say "mente"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ಧ್ಯ
    0.38
    ព្រ
    0.36
     malesuada
    0.35
     '>'
    0.35
    uddh
    0.35
     elsewhere
    0.34
    {[
    0.34
    adese
    0.33
    $[
    0.32
    ifty
    0.32
    POSITIVE LOGITS
    اً
    1.56
    ًا
    1.47
    ً
    1.23
    적으로
    1.18
    的に
    1.10
    mente
    1.05
     olarak
    1.04
    لاً
    1.02
    ically
    1.02
    amente
    1.01
    Activations Density 0.054%

    No Known Activations