© 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. 2953
    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
    य
    1.55
    ted
    1.39
    ैम
    1.36
    t
    1.34
    spaper
    1.33
    то
    1.32
    
    1.31
    te
    1.31
     яка
    1.29
    n
    1.27
    POSITIVE LOGITS
    {\
    1.12
     способ
    1.11
     timely
    1.11
    /−
    1.09
    洖
    1.09
     daw
    1.08
    isely
    1.07
     temu
    1.06
     tiếng
    1.03
    asyon
    1.03
    Activations Density 0.005%

    No Known Activations