© 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-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dispute
    0.56
    ান্তরিত
    0.52
     대한민국
    0.51
     Alabama
    0.50
     Philippines
    0.50
     hydrocarbons
    0.49
     []);
    0.48
     spirito
    0.47
    0.46
     ગુજરાત
    0.46
    POSITIVE LOGITS
    Я
    0.70
     Я
    0.60
     я
    0.59
    ît
    0.58
     отде
    0.56
    rand
    0.55
    κό
    0.55
    ков
    0.54
    ِّ
    0.54
    Ч
    0.54
    Activations Density 0.008%

    No Known Activations