© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158062
    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
    ן
    1.33
    ن
    1.29
    ם
    1.23
    n
    1.20
    ン
    1.20
     to
    1.05
    ش
    1.03
    ก
    1.02
    น
    1.01
    ع
    1.00
    POSITIVE LOGITS
    .。
    1.04
    2
    1.01
    ttä
    0.92
    tes
    0.89
    ۰۰
    0.89
    ната
    0.86
    tene
    0.86
    न्त्री
    0.83
    यों
    0.82
     are
    0.82
    Activations Density 0.000%

    No Known Activations