© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89448
    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_11_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
    os
    0.84
    n
    0.84
    es
    0.75
    ي
    0.75
    م
    0.71
    i
    0.69
    كل
    0.66
    تر
    0.66
    تو
    0.65
    كه
    0.64
    POSITIVE LOGITS
     optimisation
    0.67
     fluctuation
    0.60
     étendue
    0.60
     intensifying
    0.59
    会让
    0.59
     돼
    0.59
     classifying
    0.59
     ө
    0.57
     sensitization
    0.56
     ਜਾਂ
    0.55
    Activations Density 0.000%

    No Known Activations