© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40459
    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_11_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
    I
    0.57
    B
    0.52
    O
    0.51
     mysteries
    0.50
    My
    0.47
     dawn
    0.47
    AT
    0.45
     solutions
    0.44
    TU
    0.43
     nights
    0.43
    POSITIVE LOGITS
     eerder
    0.56
    ğun
    0.53
    愊
    0.52
     esperando
    0.51
     ਫ
    0.50
     ఎ
    0.50
    ഹ്ലാ
    0.49
    ワイ
    0.49
     వ్యా
    0.48
     இதுபோன்ற
    0.48
    Activations Density 0.000%

    No Known Activations