© 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. 139106
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities

    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
     eight
    0.57
    八
    0.51
    Eight
    0.49
     вось
    0.49
     acht
    0.48
     oito
    0.48
     Eight
    0.47
     девя
    0.46
     八
    0.45
     seven
    0.44
    POSITIVE LOGITS
     Fourteen
    0.81
     fourteenth
    0.77
     fifteenth
    0.77
     fourteen
    0.73
     ۱۴
    0.72
     Fifteen
    0.71
     Fourteenth
    0.70
     १५
    0.70
     १४
    0.69
     Sixteen
    0.68
    Activations Density 0.055%

    No Known Activations