© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218982
    Prev
    Next
    INDEX
    Explanations

    millions of people

    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_31_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
    tasks
    0.31
    varian
    0.31
    হৃত
    0.31
     pointed
    0.30
     कुर्बानी
    0.30
    voit
    0.29
    ૄ
    0.29
    products
    0.29
     Cir
    0.29
    airs
    0.29
    POSITIVE LOGITS
     ஊராட்சி
    0.32
    邑
    0.30
     witnessing
    0.29
     Bessel
    0.29
     misses
    0.29
     benzodiazep
    0.29
     Bookstore
    0.28
     embe
    0.28
     bè
    0.28
     الطيب
    0.28
    Activations Density 0.000%

    No Known Activations