© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229487
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     পৌ
    0.37
     जरुरी
    0.35
     D
    0.35
     Compensation
    0.35
     étudi
    0.34
    ੈਂ
    0.34
    pgamma
    0.34
     Сот
    0.34
    рит
    0.34
     méthod
    0.34
    POSITIVE LOGITS
    *)(
    0.38
    olateral
    0.36
    YK
    0.35
    ამაშ
    0.35
    公司的
    0.34
    ッキ
    0.34
     unis
    0.34
    ValueSet
    0.34
     ಸಮ
    0.33
     ایش
    0.33
    Activations Density 0.000%

    No Known Activations