© 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. 219550
    Prev
    Next
    INDEX
    Explanations

    dividing or clarifying what comes next

    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
     trustworthy
    0.39
     Recep
    0.38
     Сот
    0.38
    érience
    0.37
    orul
    0.37
     Nemat
    0.35
    @[
    0.35
    받
    0.35
     расположение
    0.34
     Handy
    0.34
    POSITIVE LOGITS
     ብዙውን
    0.39
    nature
    0.38
     هیچ
    0.37
     hit
    0.36
    很快
    0.36
     tended
    0.35
     undermine
    0.35
     hiçbir
    0.35
     suffer
    0.34
     miraculously
    0.34
    Activations Density 0.001%

    No Known Activations