© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210093
    Prev
    Next
    INDEX
    Explanations

    wages

    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_20_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
     unlawful
    0.41
    დის
    0.41
     ஒ
    0.38
     SU
    0.36
     curbs
    0.35
    sust
    0.35
     немец
    0.35
     German
    0.34
    ドイツ
    0.34
    Su
    0.34
    POSITIVE LOGITS
     技術
    0.40
    rá
    0.39
    onica
    0.39
    ಿತು
    0.39
    ارف
    0.38
     વિકાસ
    0.38
    ລິ
    0.38
    萺
    0.38
     playgrounds
    0.38
     дать
    0.37
    Activations Density 0.001%

    No Known Activations