© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134645
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     contempla
    0.43
     resale
    0.38
     starve
    0.38
    赉
    0.38
     ditches
    0.38
     grime
    0.37
     prizes
    0.37
     cashback
    0.37
     proposes
    0.37
     referral
    0.37
    POSITIVE LOGITS
     형태
    0.40
     መን
    0.38
    QtWidgets
    0.37
     Анд
    0.37
     형태로
    0.36
    maßen
    0.35
     ਸਿੰਘ
    0.35
    .([]
    0.35
     شكل
    0.34
     الشكل
    0.34
    Activations Density 0.000%

    No Known Activations