© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45014
    Prev
    Next
    INDEX
    Explanations

    sprite sheets

    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
     sû
    0.50
     pipe
    0.50
     designs
    0.46
    ↵
    0.45
    iz
    0.45
     bowels
    0.44
     gyms
    0.44
    pipe
    0.44
     boosts
    0.43
     p
    0.43
    POSITIVE LOGITS
     პირადი
    0.59
    PRODUCT
    0.54
     מלא
    0.54
    SubDirectory
    0.53
    TRANSFER
    0.52
    tFileInputExcel
    0.51
    КИ
    0.51
    RawO
    0.50
    Despatx
    0.50
    本机
    0.50
    Activations Density 0.010%

    No Known Activations