© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49912
    Prev
    Next
    INDEX
    Explanations

    products

    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_31_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
     downloaded
    0.40
     tracker
    0.39
    ദ്യ
    0.39
     download
    0.38
     crab
    0.37
     downloading
    0.36
     DOWNLOAD
    0.35
    𝒽
    0.35
     intranet
    0.35
     jinfo
    0.35
    POSITIVE LOGITS
     ఉత్ప
    0.66
     Products
    0.62
     productos
    0.61
     उत्पादों
    0.61
     Produtos
    0.61
     제품
    0.60
     Produkten
    0.60
     ಉತ್ಪನ್ನ
    0.60
     उत्पाद
    0.59
     producten
    0.59
    Activations Density 0.001%

    No Known Activations