© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110996
    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_2_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
    A
    1.28
    H
    1.09
    /
    1.08
    G
    1.05
    M
    1.02
    %
    0.99
    '
    0.97
    P
    0.96
    n
    0.95
    u
    0.93
    POSITIVE LOGITS
    ри
    0.96
    на
    0.93
     is
    0.89
    сно
    0.87
     are
    0.86
    يل
    0.85
    кой
    0.83
    рина
    0.83
    ले
    0.82
    лі
    0.81
    Activations Density 0.000%

    No Known Activations