© 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. 29477
    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
     家具
    0.54
    bati
    0.50
     හෝ
    0.49
     光
    0.48
     kuchen
    0.47
     heist
    0.47
     unscrupulous
    0.47
     Möbel
    0.46
    ษฐ
    0.46
     monetary
    0.45
    POSITIVE LOGITS
    ते
    0.52
    Add
    0.51
    add
    0.50
    Load
    0.50
    Какой
    0.50
    Ό
    0.50
    ovel
    0.49
    Att
    0.49
    intero
    0.47
    variant
    0.47
    Activations Density 0.000%

    No Known Activations