© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90428
    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_60_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
    )-$
    0.43
     gw
    0.42
    b
    0.39
    bP
    0.38
     eight
    0.38
    निज
    0.38
    BibitemShut
    0.37
     fB
    0.37
    iters
    0.37
    bR
    0.37
    POSITIVE LOGITS
     (
    0.57
     for
    0.57
    (
    0.54
     To
    0.51
     For
    0.46
    4
    0.45
     Fully
    0.44
     Front
    0.44
    ...
    0.43
    (...)
    0.43
    Activations Density 0.000%

    No Known Activations