© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8939
    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_3_width_262k_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
    要
    2.85
    tained
    2.43
    taining
    2.38
     homeomorphic
    2.37
     ordinate
    2.36
     явля
    2.33
     impoverished
    2.25
     seater
    2.25
     مثبت
    2.22
    贿
    2.20
    POSITIVE LOGITS
    ка
    2.33
    но
    2.28
    р
    2.19
    getData
    2.18
    am
    2.09
    ार
    2.04
    ек
    1.98
    фри
    1.97
    ный
    1.96
     شاء
    1.92
    Activations Density 0.100%

    No Known Activations