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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2381
    Prev
    Next
    INDEX
    Explanations

    help="

    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
     الخدمات
    0.31
     देशभर
    0.30
     ബാല
    0.30
    临
    0.29
     outputPath
    0.29
     کودکان
    0.29
     امام
    0.28
    NDAY
    0.28
    髡
    0.28
    ndown
    0.27
    POSITIVE LOGITS
    Book
    0.29
     book
    0.29
    Phong
    0.28
    listed
    0.27
    Pho
    0.27
    Trimethyl
    0.26
     strange
    0.26
    interno
    0.26
    תי
    0.26
    riez
    0.25
    Activations Density 0.062%

    No Known Activations