© 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. 3249
    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
    ع
    0.72
    dbjc
    0.69
    n
    0.69
    ло
    0.59
    ল
    0.58
    lo
    0.58
    på
    0.58
    न
    0.57
    uuuu
    0.57
    نا
    0.56
    POSITIVE LOGITS
     poter
    0.60
    𝑘
    0.58
    uyor
    0.57
    的目的
    0.56
     архівів
    0.55
     ello
    0.54
    ^{\
    0.53
     categ
    0.52
     poder
    0.52
    𝑜
    0.51
    Activations Density 0.431%

    No Known Activations