© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116625
    Prev
    Next
    INDEX
    Explanations

    URLs, code namespaces, and definitions

    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_38_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
    驁
    0.43
     Vase
    0.41
     Objekte
    0.40
     CHINA
    0.38
     Adapted
    0.38
    峤
    0.38
    谲
    0.38
    ়া
    0.37
    甯
    0.37
     feste
    0.36
    POSITIVE LOGITS
    蛀
    0.39
    メンテナンス
    0.37
    🥕
    0.37
    Fire
    0.36
     melting
    0.36
    UITableView
    0.35
    bacteria
    0.35
    Sax
    0.35
    ပြည်
    0.35
    Bird
    0.34
    Activations Density 0.000%

    No Known Activations