© 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. 1538
    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
    s
    2.67
    ات
    2.55
    প
    2.36
    ের
    2.32
    ج
    2.16
    Роз
    2.11
    ों
    2.05
    Housing
    2.04
     subnet
    2.02
    Outputs
    2.02
    POSITIVE LOGITS
    ا
    2.23
     불구하고
    2.07
    ية
    1.83
    もちろん
    1.79
    ital
    1.78
    ওলানা
    1.77
     suo
    1.74
     bienvenidos
    1.73
    ה
    1.73
    ized
    1.69
    Activations Density 0.326%

    No Known Activations