© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99684
    Prev
    Next
    INDEX
    Explanations

    Six Sigma defects

    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_16_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
     Boogie
    0.47
    播出
    0.45
     rassembl
    0.44
     saath
    0.44
    帽
    0.43
     സുമിത്ര
    0.43
     Macaulay
    0.43
    ０
    0.42
     inescap
    0.42
    まとめ
    0.42
    POSITIVE LOGITS
    div
    0.49
    zin
    0.47
    nya
    0.44
    yl
    0.43
    HLER
    0.43
    dr
    0.43
    ns
    0.42
    series
    0.42
    wohner
    0.41
    िडिओ
    0.41
    Activations Density 0.000%

    No Known Activations