© 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. 51004
    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
    ){}
    0.56
     उच्चारण
    0.52
     Συ
    0.50
     अबा
    0.50
    ativas
    0.49
     самые
    0.49
     лекар
    0.49
     видеть
    0.49
    ?)
    0.48
     অবা
    0.48
    POSITIVE LOGITS
    P
    0.54
    ium
    0.53
    است
    0.50
    位
    0.49
    本
    0.48
    illing
    0.47
     mehr
    0.46
     neuf
    0.46
    into
    0.46
    וי
    0.46
    Activations Density 0.000%

    No Known Activations