© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134260
    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_6_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
    ы
    0.95
    </h2>
    0.91
    是
    0.90
    ों
    0.87
    </u>
    0.82
    Y
    0.82
    Й
    0.80
     y
    0.80
    that
    0.80
    تا
    0.79
    POSITIVE LOGITS
    in
    1.42
    ين
    1.33
    c
    1.18
    g
    1.17
    a
    1.14
    v
    1.08
    oc
    1.05
    f
    0.95
    el
    0.94
    ку
    0.93
    Activations Density 0.000%

    No Known Activations