© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222110
    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_10_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
     at
    0.55
     al
    0.52
     to
    0.50
    ه
    0.50
     Glas
    0.48
     Stanford
    0.48
     glas
    0.47
    ا
    0.47
      
    0.46
    glas
    0.46
    POSITIVE LOGITS
     война
    0.57
    ۶
    0.55
    <unused617>
    0.54
    <unused2037>
    0.54
    <unused723>
    0.52
    ६
    0.52
    =_
    0.51
    ඛ
    0.51
    <unused1012>
    0.51
    <unused506>
    0.51
    Activations Density 0.000%

    No Known Activations