© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52629
    Prev
    Next
    INDEX
    Explanations

    Award Best Emmy Grammy Academy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    MDA
    0.43
     заду
    0.36
    Disp
    0.36
    Daw
    0.36
     Budd
    0.35
    暑
    0.34
     сі
    0.34
    Fri
    0.34
    egi
    0.34
     DISTRIBUTION
    0.34
    POSITIVE LOGITS
    SelectionSet
    0.38
     inherit
    0.37
    keepers
    0.36
     quedar
    0.36
    效果
    0.35
     Slovenia
    0.35
     odnos
    0.35
     acrob
    0.35
     式
    0.34
    ifndef
    0.34
    Activations Density 0.003%

    No Known Activations