© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134880
    Prev
    Next
    INDEX
    Explanations

    Latin words and phrases

    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_1_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
    но
    1.14
    ку
    1.13
    p
    1.13
    ي
    1.13
    ן
    1.04
    μα
    1.01
     increases
    0.97
    μπ
    0.97
    ні
    0.95
    ﺪ
    0.95
    POSITIVE LOGITS
    :
    1.34
    .
    1.03
     autora
    0.90
    il
    0.89
     různ
    0.89
    ról
    0.87
    '
    0.86
    ليك
    0.85
    ب
    0.85
     conti
    0.84
    Activations Density 0.009%

    No Known Activations