© 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. 210051
    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
    س
    0.67
    ف
    0.59
    ス
    0.56
    sa
    0.55
    ج
    0.54
    ると
    0.54
    psies
    0.54
    smöglichkeiten
    0.53
    ting
    0.52
    د
    0.52
    POSITIVE LOGITS
     demanding
    0.61
     dependence
    0.55
     observability
    0.52
     source
    0.52
     mnemonic
    0.52
     bibliographic
    0.51
     judgment
    0.50
     vigilance
    0.49
     teamwork
    0.49
     rollback
    0.48
    Activations Density 0.000%

    No Known Activations