© 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. 31446
    Prev
    Next
    INDEX
    Explanations

    connector words, structure

    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
     Hicks
    0.32
     \...
    0.30
     \[
    0.29
     mnog
    0.29
     \"
    0.28
     \#
    0.28
     camion
    0.28
    ген
    0.28
     \*
    0.28
    াহীন
    0.27
    POSITIVE LOGITS
    ங்களும்
    0.31
    aval
    0.29
    هاي
    0.29
    Bei
    0.29
    Jag
    0.28
    एफटी
    0.28
    Ђ
    0.28
    ופן
    0.28
    ᐊ
    0.28
     পাকিস্তানীরা
    0.27
    Activations Density 0.126%

    No Known Activations