© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2279
    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
    ن
    2.56
    на
    2.55
     userRoutes
    2.46
    ა
    2.35
    లో
    2.34
    ة
    2.25
    ни
    2.22
     consigui
    2.15
    рона
    2.14
    printStackTrace
    2.14
    POSITIVE LOGITS
     numerator
    2.65
     embarking
    2.41
    $('#
    2.31
    <0x80>
    2.30
    gment
    2.30
    vaise
    2.29
    메이션
    2.28
     monet
    2.28
     twos
    2.28
     Microbial
    2.24
    Activations Density 0.002%

    No Known Activations