© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82964
    Prev
    Next
    INDEX
    Explanations

    mixed code and languages

    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_53_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
     Ü
    0.46
     Ubisoft
    0.39
     Ú
    0.39
    巴
    0.38
    Ư
    0.38
    Ü
    0.37
    BASELINE
    0.36
    ERATE
    0.36
    Ú
    0.36
    ercase
    0.36
    POSITIVE LOGITS
     vir
    0.41
     vire
    0.41
    Articles
    0.40
     Gideon
    0.39
     Gori
    0.38
     Vir
    0.38
    峨
    0.38
    iguo
    0.38
    articles
    0.37
     खंड
    0.37
    Activations Density 0.000%

    No Known Activations