© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47145
    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_13_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
     avocados
    0.60
     claimed
    0.59
    𝐁
    0.55
     secondi
    0.54
     teaspoons
    0.53
     susu
    0.51
     आपकी
    0.50
     comunicado
    0.50
     sofas
    0.50
     lavado
    0.50
    POSITIVE LOGITS
    樋
    0.58
    本当に
    0.51
    Psych
    0.49
    jh
    0.47
    !(
    0.46
     wirklich
    0.45
    Really
    0.44
    രിക
    0.44
    getPath
    0.44
    phthalm
    0.44
    Activations Density 0.000%

    No Known Activations