© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256232
    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    er
    1.50
    yzed
    1.10
    d
    1.09
    jeno
    1.07
    ettes
    1.05
    ɹ
    1.04
    dni
    1.04
    kę
    1.03
    et
    1.03
    ются
    1.03
    POSITIVE LOGITS
    seasonal
    1.35
     pond
    1.33
    ڤ
    1.16
     بلوچستان
    1.16
     specificity
    1.16
     seasonally
    1.15
     roof
    1.15
    梦想
    1.14
    atakan
    1.13
    pendiente
    1.10
    Activations Density 0.000%

    No Known Activations