© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170465
    Prev
    Next
    INDEX
    Explanations

    construction completion dates

    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
    Negative Logits
    ্যন্ত
    0.40
    ﺖ
    0.37
    茁
    0.36
    hydroxy
    0.34
     انتہائی
    0.34
     متعلقه
    0.34
    более
    0.34
     CAUSED
    0.34
    應該
    0.34
    നിന്ന്
    0.34
    POSITIVE LOGITS
     युवाओ
    0.35
     assembly
    0.32
    埂
    0.32
     ―
    0.31
    assembling
    0.31
    ज़ा
    0.30
     따로
    0.30
     assembled
    0.30
    って
    0.29
    ₀
    0.29
    Activations Density 0.001%

    No Known Activations