© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199040
    Prev
    Next
    INDEX
    Explanations

    SQL schema definitions

    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_46_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
    HandleFunc
    0.33
    शत
    0.31
    ORDAN
    0.30
    Enfin
    0.30
    Editable
    0.29
    ორცი
    0.29
    %")
    0.28
     মন্ত
    0.28
    డ్‌
    0.28
    靦
    0.28
    POSITIVE LOGITS
     su
    0.33
     output
    0.30
    las
    0.29
     Sink
    0.29
     les
    0.28
     П
    0.28
     Q
    0.28
     las
    0.28
     extrav
    0.27
     sink
    0.27
    Activations Density 0.008%

    No Known Activations