© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4556
    Prev
    Next
    INDEX
    Explanations

    express.errorHandler, express.json, express();

    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_39_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
     близь
    0.41
    ঞ্চি
    0.38
    离子
    0.38
    Windows
    0.37
    ሽታ
    0.37
    phenyl
    0.37
     /$
    0.37
    慰
    0.37
     ODBC
    0.36
     Windows
    0.36
    POSITIVE LOGITS
     Шо
    0.35
     morgan
    0.35
     పె
    0.35
     সিদ্দিক
    0.35
     static
    0.34
     Alderman
    0.34
     inst
    0.34
     fur
    0.33
     -----------
    0.33
    õe
    0.33
    Activations Density 0.001%

    No Known Activations