© 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. 224247
    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
     renovation
    0.49
    <0xA8>
    0.47
     domestic
    0.47
     decoder
    0.45
     denunci
    0.44
    ור
    0.44
     Differ
    0.43
     parade
    0.43
    لت
    0.43
    Descrição
    0.42
    POSITIVE LOGITS
     атмосфер
    0.62
    অনেক
    0.60
     pdelay
    0.57
     Eshelby
    0.57
    芓
    0.56
     гульнявыя
    0.55
     오히려
    0.54
    ointers
    0.54
     imme
    0.54
     atmosfera
    0.53
    Activations Density 0.000%

    No Known Activations