© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46317
    Prev
    Next
    INDEX
    Explanations

    article titles or headings

    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_13_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
     omega
    0.55
    nahmen
    0.53
    ولندا
    0.51
    //!
    0.50
    ر
    0.50
    الب
    0.49
    Hr
    0.49
     ఇండియా
    0.49
     hydroxy
    0.48
    》，
    0.48
    POSITIVE LOGITS
    psons
    0.50
    矶
    0.50
    gera
    0.49
     কলকাতায়
    0.48
     percussion
    0.48
     yö
    0.47
     planilha
    0.47
    мс
    0.47
     séquence
    0.47
    go
    0.47
    Activations Density 0.010%

    No Known Activations