© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83021
    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_0_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
    子の
    1.70
    اری
    1.68
    <0x0D>
    1.63
    </h4>
    1.53
    は
    1.44
    یاء
    1.41
    ී
    1.39
    </h2>
    1.37
    ные
    1.36
    ِی
    1.34
    POSITIVE LOGITS
    ne
    2.33
     in
    2.23
    st
    2.08
    ma
    1.94
    d
    1.91
     a
    1.84
    w
    1.77
    p
    1.73
    ning
    1.71
    ed
    1.70
    Activations Density 0.000%

    No Known Activations