© 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. 3283
    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
    eenth
    3.27
    inerary
    3.23
    го
    2.89
     raining
    2.84
    情况下
    2.66
    THING
    2.62
    र
    2.60
     предусмотре
    2.57
     своего
    2.54
    raining
    2.53
    POSITIVE LOGITS
    ों
    3.34
    sion
    3.15
    s
    2.75
    छाड़
    2.60
    ség
    2.55
     ais
    2.46
    Prosecutors
    2.44
    sı
    2.42
    可以将
    2.41
    schaft
    2.38
    Activations Density 0.265%

    No Known Activations