© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59728
    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_11_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
     جنبي
    0.48
    انس
    0.47
    ит
    0.46
    ани
    0.46
    ابية
    0.46
    听
    0.45
     PropTypes
    0.45
    單
    0.45
     Iod
    0.44
    ките
    0.44
    POSITIVE LOGITS
     westward
    0.58
     bankruptcy
    0.54
     refueling
    0.53
     southward
    0.52
     hypothesis
    0.52
     physics
    0.51
     mathematical
    0.51
     epidemic
    0.50
     marvellous
    0.50
     northward
    0.50
    Activations Density 0.000%

    No Known Activations