© 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. 256398
    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
    ০
    1.09
    र
    1.03
    ר
    0.98
     súa
    0.97
    ず
    0.95
    ெழு
    0.95
     Mines
    0.95
     ولك
    0.93
     هي
    0.92
     горных
    0.92
    POSITIVE LOGITS
     clín
    1.50
     llvm
    1.45
    ಳಿಗೆ
    1.44
    šće
    1.41
     mindset
    1.41
    Paf
    1.39
     percentile
    1.38
     đứng
    1.37
    💭
    1.37
    𝒅
    1.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.