© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145263
    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_18_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
     Omphalodes
    0.64
     ڈھاکہ
    0.58
    hattim
    0.58
    меся
    0.57
    linker
    0.56
     HTMLElement
    0.55
    
    0.55
    reactant
    0.54
     صہیونیت
    0.54
    joins
    0.53
    POSITIVE LOGITS
    การ
    0.55
    ير
    0.55
    ني
    0.52
    다
    0.52
    és
    0.52
    斯
    0.51
    ق
    0.50
    يس
    0.48
    א
    0.48
    ين
    0.48
    Activations Density 0.000%

    No Known Activations