© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 960
    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
    Cancel
    0.32
    C
    0.29
    nommen
    0.28
     hoch
    0.27
     (
    0.26
     insbesondere
    0.26
     hospitalized
    0.26
     سبتمبر
    0.25
     terutama
    0.25
     وغيرها
    0.25
    POSITIVE LOGITS
    UILLER
    0.35
    ванне
    0.34
     券
    0.33
    निंग
    0.33
    ování
    0.33
     postérieur
    0.32
    जीशन
    0.32
    Ễ
    0.32
    ДИ
    0.32
    вающий
    0.31
    Activations Density 0.109%

    No Known Activations