© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17027
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide fixation

    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_15_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
     isometry
    0.53
    InfoHeader
    0.51
     consumption
    0.50
     hill
    0.50
     chimney
    0.50
    ին
    0.48
     injure
    0.48
    ྛ
    0.48
     larceny
    0.48
    violence
    0.48
    POSITIVE LOGITS
     Вол
    0.64
     Tef
    0.63
     Peacock
    0.57
     ر
    0.54
     グ
    0.54
     Harry
    0.53
     ملف
    0.52
     Viva
    0.51
     r
    0.51
     Harcourt
    0.51
    Activations Density 0.004%

    No Known Activations