© 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. 29506
    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
    ínguez
    0.54
     Carpath
    0.51
     दुनिया
    0.51
    BeerItem
    0.50
    éreo
    0.49
    entemente
    0.48
     ϒ
    0.48
     Gutiérrez
    0.48
    ности
    0.48
    л
    0.48
    POSITIVE LOGITS
    ";
    0.54
    '";
    0.52
     Speak
    0.51
    ’
    0.51
    anyone
    0.49
    quantitative
    0.49
    party
    0.48
     miệng
    0.48
    issue
    0.47
    futures
    0.47
    Activations Density 0.000%

    No Known Activations