© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 961
    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
    я
    3.77
    Trem
    2.86
     Поскольку
    2.74
    г
    2.65
    ول
    2.64
    ሲ
    2.60
    {
    2.60
    ˝
    2.59
    ет
    2.59
    Trajectory
    2.57
    POSITIVE LOGITS
    ל
    2.77
    ן
    2.71
    會
    2.56
    ោង
    2.48
    teil
    2.48
    inertia
    2.43
    ট
    2.42
    BLINK
    2.38
    ので
    2.37
     pois
    2.37
    Activations Density 0.086%

    No Known Activations