© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62709
    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
    Negative Logits
     was
    0.54
     n
    0.53
    I
    0.52
    b
    0.52
     I
    0.51
     va
    0.51
    cus
    0.50
    cion
    0.50
     logic
    0.48
     |_{
    0.48
    POSITIVE LOGITS
    ?’”
    0.53
    oração
    0.50
    PROM
    0.50
    여자
    0.50
    लीस
    0.50
    ٧
    0.48
    ла
    0.48
    的問題
    0.47
    די
    0.47
     عرص
    0.47
    Activations Density 0.000%

    No Known Activations