© 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. 4263
    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
    দের
    3.73
    𝗱
    3.53
    SHE
    2.94
    𝗴
    2.92
    𝗧
    2.88
     Nossa
    2.84
    𝘇
    2.83
    ال
    2.76
     खासा
    2.72
     anger
    2.70
    POSITIVE LOGITS
    ش
    3.47
    ้
    2.71
    要
    2.52
    要做
    2.52
     불구하고
    2.46
    其他
    2.45
    ല്ലാം
    2.38
    tedir
    2.38
    ত্ব
    2.38
    要想
    2.36
    Activations Density 0.035%

    No Known Activations