© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180024
    Prev
    Next
    INDEX
    Explanations

    Midnight or Jim

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ুইস
    0.42
    eker
    0.40
     fascinated
    0.38
    垕
    0.38
     obsessed
    0.38
    ósfera
    0.38
     arrangements
    0.37
    ossa
    0.37
     Flan
    0.37
     ade
    0.37
    POSITIVE LOGITS
    Midnight
    0.42
     जिम
    0.42
    acknowledge
    0.42
     સ
    0.40
    imha
    0.39
    ิ้น
    0.39
    midnight
    0.39
     Midnight
    0.38
     SINGH
    0.38
    Jim
    0.37
    Activations Density 0.000%

    No Known Activations