© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4172
    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_2_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
    р
    1.90
    TEL
    1.90
    НГ
    1.85
    KeyDown
    1.84
     ari
    1.84
     ï
    1.83
    ëm
    1.82
    mice
    1.79
    itio
    1.76
     $('
    1.76
    POSITIVE LOGITS
     πως
    1.93
    ність
    1.91
    o
    1.89
     кстати
    1.67
     overwhelm
    1.66
    л
    1.61
    ്
    1.59
     definitivo
    1.56
    ం
    1.56
    zur
    1.56
    Activations Density 0.006%

    No Known Activations