© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13624
    Prev
    Next
    INDEX
    Explanations

    numbers following slashes or periods

    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_15_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
     public
    0.56
     H
    0.55
     generator
    0.54
     direct
    0.54
     specific
    0.54
     web
    0.53
     generated
    0.53
     All
    0.52
     full
    0.52
     created
    0.51
    POSITIVE LOGITS
    ш
    0.63
     ৩২
    0.50
    他們的
    0.50
    浱
    0.50
     их
    0.49
     Их
    0.49
    Vr
    0.48
    。)
    0.48
    vora
    0.48
     njihov
    0.47
    Activations Density 0.001%

    No Known Activations