© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1199
    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
    ва
    2.47
    ة
    2.46
     svm
    2.29
     balsamic
    2.22
     lineColor
    2.20
     veniam
    2.17
    ,}$
    2.13
    𝐣
    2.12
     probado
    2.12
     oftent
    2.07
    POSITIVE LOGITS
    u
    4.19
    z
    3.06
    l
    3.03
    m
    2.95
    a
    2.71
    an
    2.69
    ことになる
    2.67
    %>%
    2.64
    i
    2.63
    一个
    2.60
    Activations Density 0.029%

    No Known Activations