© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90295
    Prev
    Next
    INDEX
    Explanations

    Error processing files

    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_23_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
     ולא
    0.40
     ليس
    0.39
     albeit
    0.38
     Directeur
    0.38
     journaliste
    0.38
     niet
    0.37
    albeit
    0.37
     لإ
    0.37
    ྔ
    0.36
     тър
    0.36
    POSITIVE LOGITS
    শিশু
    0.42
     failed
    0.40
    Church
    0.40
     occured
    0.40
    Action
    0.40
     Church
    0.39
    াকৃতিক
    0.39
    Hear
    0.36
     बढ़ोतरी
    0.35
    Пра
    0.35
    Activations Density 0.011%

    No Known Activations