© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35850
    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_7_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
    Mét
    0.67
     خواهد
    0.67
    Math
    0.66
    葆
    0.61
    ۳
    0.61
    File
    0.60
    Câu
    0.60
    ួរ
    0.60
    Objet
    0.59
    ají
    0.58
    POSITIVE LOGITS
    s
    0.61
    als
    0.59
     времена
    0.59
    지
    0.58
     excellently
    0.54
     aq
    0.53
     pemimpin
    0.52
     HOURS
    0.51
     basso
    0.50
     XY
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.