© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46596
    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_3_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
     for
    1.02
    is
    1.01
    1
    1.01
    al
    0.89
     (
    0.89
    el
    0.86
    ers
    0.86
     by
    0.85
    es
    0.84
    re
    0.84
    POSITIVE LOGITS
    ма
    0.82
    ように
    0.76
     bhave
    0.76
    splitLength
    0.75
    𒅴
    0.73
    ک
    0.71
     فونبټ
    0.71
    ынша
    0.70
    もら
    0.70
     čovjek
    0.70
    Activations Density 0.000%

    No Known Activations