© 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. 2599
    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
    Lors
    2.52
    ل
    2.29
     これ
    2.22
    dueDate
    2.18
    $
    2.17
    তার
    2.16
    JlcG
    2.12
    Исто
    2.11
     dehuman
    2.09
    歐
    2.09
    POSITIVE LOGITS
     खासा
    3.25
    р
    2.67
    ే
    2.50
    uje
    2.27
     вероятность
    2.25
     sorte
    2.24
    enough
    2.23
    로
    2.15
     непло
    2.15
    ן
    2.11
    Activations Density 0.019%

    No Known Activations