© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142398
    Prev
    Next
    INDEX
    Explanations

    search engine

    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
    ケット
    0.41
    phus
    0.40
     cranking
    0.40
     upright
    0.39
     carrying
    0.39
     carried
    0.38
     pumping
    0.38
    诨
    0.38
     pumps
    0.38
     oversight
    0.37
    POSITIVE LOGITS
    search
    0.60
     Search
    0.54
    Search
    0.53
     البحث
    0.52
     Goog
    0.50
    research
    0.50
    GOOGLE
    0.50
     goog
    0.49
     search
    0.48
     SEARCH
    0.48
    Activations Density 0.013%

    No Known Activations