© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194217
    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_4_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
    ग
    0.51
    ław
    0.48
    óa
    0.47
    금이
    0.47
    ahl
    0.46
    ệu
    0.46
    런
    0.46
    elh
    0.46
    День
    0.45
    okit
    0.45
    POSITIVE LOGITS
     Tabel
    0.48
    sentiment
    0.47
     Bourgoin
    0.45
     Algorithms
    0.44
     italic
    0.43
     মিড
    0.43
     😄
    0.42
     العلماء
    0.42
     Cout
    0.41
     Activate
    0.41
    Activations Density 0.000%

    No Known Activations