© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43683
    Prev
    Next
    INDEX
    Explanations

    network types and insurance plans

    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
    𝙘
    0.52
     અથવા
    0.46
     bact
    0.45
     aumenta
    0.45
    пой
    0.43
     atrav
    0.43
     或
    0.43
    或
    0.43
     или
    0.42
     punctatis
    0.42
    POSITIVE LOGITS
    ood
    0.40
    itel
    0.40
    ivano
    0.39
    uring
    0.39
    고
    0.39
    itches
    0.38
    ंग
    0.38
    ering
    0.38
    iche
    0.38
    ቀ
    0.38
    Activations Density 0.001%

    No Known Activations