© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118166
    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_27_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
    脸
    0.40
    UIImage
    0.40
     एस्ट्र
    0.37
     ನಾನು
    0.36
    bangan
    0.36
    但我
    0.35
    ⁦
    0.34
     क्वेश्चंस
    0.34
    LinearLayout
    0.34
    BufferedImage
    0.34
    POSITIVE LOGITS
     etc
    0.39
     Angola
    0.37
     (~
    0.36
     back
    0.36
     Lebanon
    0.34
     intrac
    0.34
     впоследствии
    0.33
     reproduc
    0.33
     tilbage
    0.33
     вскоре
    0.33
    Activations Density 0.000%

    No Known Activations