© 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. 4220
    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
    eworthy
    2.45
    е
    2.33
    aný
    2.17
    শীল
    2.12
    റ്റ്
    2.10
     проведен
    2.09
     necessari
    2.03
    いません
    2.02
     MessageBox
    2.00
     সচিব
    2.00
    POSITIVE LOGITS
    ם
    3.15
    स
    2.71
    dé
    2.47
     kelamin
    2.37
    شنبه
    2.22
    ፍተኛ
    2.22
    Gambar
    2.12
     daim
    2.08
    გუფი
    2.04
    ρός
    2.04
    Activations Density 0.019%

    No Known Activations