© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2371
    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_12_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
    partisan
    0.75
    いただ
    0.75
    渑
    0.72
     comprado
    0.72
    ureshi
    0.72
    itaea
    0.70
     onDestroy
    0.70
     숙
    0.69
    catenin
    0.68
    kušen
    0.68
    POSITIVE LOGITS
     [#
    0.64
     slots
    0.63
     apron
    0.59
    -[
    0.58
     gazebo
    0.58
     [
    0.58
    боры
    0.58
    3
    0.57
     gardeners
    0.56
    4
    0.56
    Activations Density 0.000%

    No Known Activations