© 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. 4074
    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
     impetus
    2.34
    tains
    2.30
    ties
    2.26
    tttt
    2.09
    ت
    2.09
    tained
    2.04
    従
    2.02
     joys
    1.99
    tting
    1.98
     kèm
    1.96
    POSITIVE LOGITS
    틈
    2.43
    к
    2.30
    ло
    1.97
    োড
    1.91
    ɖ
    1.78
     journée
    1.76
    েজ
    1.73
    дун
    1.71
     haut
    1.69
    ра
    1.68
    Activations Density 0.027%

    No Known Activations