© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203142
    Prev
    Next
    INDEX
    Explanations

    years and number/date formats

    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_25_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
     jell
    0.38
     swivel
    0.37
     brunch
    0.34
    షన్‌
    0.34
     textbook
    0.32
     বাস্তবায়
    0.32
     collateral
    0.31
    त्‍
    0.31
    Ⅱ
    0.31
     amenity
    0.31
    POSITIVE LOGITS
     इंस्टीट्यूट
    0.40
     oleh
    0.39
     توسط
    0.37
    gült
    0.36
     obtained
    0.36
     seura
    0.36
    嚶
    0.35
    umno
    0.35
    Ė
    0.35
     przep
    0.34
    Activations Density 0.000%

    No Known Activations