© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225476
    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_10_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
     x
    0.71
     r
    0.68
    0.57
     l
    0.56
     discuter
    0.50
     plusieurs
    0.49
     X
    0.48
     Probleme
    0.48
     i
    0.47
     lle
    0.47
    POSITIVE LOGITS
    強い
    0.54
    को
    0.52
    емов
    0.52
    ecast
    0.51
    ओं
    0.51
     cảnh
    0.51
    in
    0.50
    막
    0.49
    σε
    0.48
    s
    0.48
    Activations Density 0.000%

    No Known Activations