© 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. 226136
    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
    son
    0.66
    asing
    0.66
    fy
    0.64
    (
    0.61
    State
    0.59
    iny
    0.59
    na
    0.57
    ara
    0.56
    kir
    0.54
    SError
    0.54
    POSITIVE LOGITS
     componenti
    0.50
     чув
    0.47
    ଉ
    0.46
     структур
    0.46
     scompar
    0.46
     fórm
    0.46
     credited
    0.45
     facteur
    0.45
     причин
    0.44
     всем
    0.44
    Activations Density 0.000%

    No Known Activations