© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28165
    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
    ;">
    0.56
    us
    0.50
    Course
    0.48
    Service
    0.46
    Act
    0.45
    Ac
    0.45
    र
    0.45
    Group
    0.45
    সুর
    0.45
    Ag
    0.44
    POSITIVE LOGITS
     subsets
    0.56
     landlab
    0.54
     adiabatic
    0.50
     выбра
    0.50
    autoarima
    0.50
     ము
    0.50
     Brav
    0.48
     handouts
    0.47
    <unused1801>
    0.47
    టో
    0.47
    Activations Density 0.000%

    No Known Activations