© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137728
    Prev
    Next
    INDEX
    Explanations

    Master of Arts or Science degrees

    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_37_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
    Season
    0.47
     season
    0.43
    季
    0.43
    SEASON
    0.43
    season
    0.42
     seizoen
    0.42
    aned
    0.41
     Seasons
    0.41
     Season
    0.41
     Lakh
    0.40
    POSITIVE LOGITS
     rodent
    0.60
     rabbit
    0.57
     thesis
    0.56
     hamster
    0.56
     snake
    0.54
     Rabbit
    0.51
     tesis
    0.50
    蛇
    0.50
     viper
    0.50
    rabbit
    0.49
    Activations Density 0.013%

    No Known Activations