© 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. 4122
    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
    我
    1.83
    ك
    1.81
    strawberry
    1.74
     وط
    1.74
    -\
    1.67
    xn
    1.65
    ोप
    1.64
    お
    1.62
    neq
    1.62
    meth
    1.57
    POSITIVE LOGITS
     Именно
    1.96
    ят
    1.65
     Ländern
    1.59
     amelyek
    1.58
     Selon
    1.56
    ્લા
    1.53
     რომლებიც
    1.52
    एर
    1.51
     soorten
    1.51
     உள்ளன
    1.49
    Activations Density 0.725%

    No Known Activations