© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78470
    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_0_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
    on
    0.58
    at
    0.56
    atche
    0.48
    0
    0.48
    diagn
    0.47
    1
    0.47
    ant
    0.47
     cryptic
    0.47
    3
    0.47
    审查
    0.46
    POSITIVE LOGITS
    𒂍
    0.55
     Ў
    0.53
     À
    0.52
    ?»
    0.52
     LongNumber
    0.50
     الأمير
    0.50
     Sumber
    0.49
     Philippine
    0.48
     Однако
    0.47
    ?}
    0.47
    Activations Density 0.000%

    No Known Activations