© 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. 3920
    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
    Not in Any Lists

    No Comments

    Negative Logits
    д
    1.28
    ف
    1.18
    ق
    1.14
    ab
    1.01
     ley
    0.97
    к
    0.96
    на
    0.96
    ك
    0.95
    v
    0.95
    ק
    0.95
    POSITIVE LOGITS
    تى
    1.00
    ्य
    1.00
    ம்
    0.97
    ه
    0.96
    ках
    0.87
    ுங்கள்
    0.86
     Эта
    0.85
    ﺓ
    0.84
    রো
    0.83
    amerikan
    0.82
    Activations Density 0.026%

    No Known Activations