© 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. 207062
    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
     myopia
    0.61
    ਮ
    0.61
    ﻤ
    0.59
    Μ
    0.57
    COMANDA
    0.56
    цима
    0.56
     škole
    0.55
     М
    0.54
     lawyers
    0.54
     glaucoma
    0.54
    POSITIVE LOGITS
    on
    0.79
    ana
    0.65
    and
    0.61
    aru
    0.59
    ec
    0.56
    ampton
    0.56
    ani
    0.53
    hess
    0.53
    bound
    0.52
    arte
    0.52
    Activations Density 0.000%

    No Known Activations