© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43466
    Prev
    Next
    INDEX
    Explanations

    the oldest, new, same, star, village, defending, main, sage

    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_22_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
    胍
    0.25
     спів
    0.25
     ጎ
    0.24
     ایسے
    0.24
    Somos
    0.24
     ות
    0.23
     συνέχ
    0.23
     protracted
    0.23
     य
    0.23
     excursions
    0.23
    POSITIVE LOGITS
     helper
    0.31
     despre
    0.27
     kategori
    0.26
    仮想
    0.26
    ანი
    0.26
     helpers
    0.26
    ანა
    0.25
    ान्स
    0.25
    क्सी
    0.25
     Helper
    0.25
    Activations Density 0.006%

    No Known Activations