© 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. 223165
    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
    prevent
    0.55
    i
    0.54
    School
    0.49
    an
    0.46
    k
    0.46
    chool
    0.45
    forest
    0.45
    xxxx
    0.45
    Prevent
    0.45
    lement
    0.44
    POSITIVE LOGITS
     granules
    0.56
    흐
    0.52
     salicylic
    0.50
     granule
    0.50
     можливість
    0.50
     Adrián
    0.48
     pulverized
    0.47
     recirc
    0.47
     Debi
    0.47
     positrons
    0.46
    Activations Density 0.000%

    No Known Activations