© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204679
    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
    ا
    1.01
    प
    0.99
    бо
    0.96
    in
    0.94
    在
    0.91
    다
    0.91
     in
    0.90
    aría
    0.89
    া
    0.87
    \
    0.86
    POSITIVE LOGITS
     NASCAR
    0.88
     renormal
    0.87
     כי
    0.85
    that
    0.82
    時は
    0.82
     ആൻ
    0.82
    ur
    0.82
    ור
    0.81
    ಾರ
    0.81
    c
    0.81
    Activations Density 0.000%

    No Known Activations