© 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. 2704
    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
    それ
    0.32
     Zukunft
    0.32
     déprimées
    0.30
     lagged
    0.30
     AppPage
    0.30
    ވި
    0.30
    ින
    0.30
    ോട്ട്
    0.29
     samtidigt
    0.29
    ኖ
    0.29
    POSITIVE LOGITS
     your
    0.35
    van
    0.35
    guan
    0.35
     profess
    0.34
     jovem
    0.34
     votre
    0.33
    your
    0.32
     jeune
    0.32
    hese
    0.32
    wan
    0.32
    Activations Density 0.099%

    No Known Activations