© 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. 50271
    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
    ிகள்
    0.75
    いますが
    0.71
    )!
    0.64
     typographic
    0.64
    ۰
    0.63
    ありますが
    0.61
    ่า
    0.61
     combustível
    0.60
    ',
    0.58
    ",
    0.58
    POSITIVE LOGITS
    re
    1.13
    on
    1.11
    e
    1.02
    en
    0.94
    ru
    0.93
    au
    0.89
    er
    0.88
    n
    0.88
    an
    0.82
    a
    0.81
    Activations Density 0.004%

    No Known Activations