© 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. 568
    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
     불구하고
    2.00
    一丝
    1.61
    NSInteger
    1.56
     البح
    1.55
    াপ
    1.54
     imageHeight
    1.54
     reluctance
    1.50
    ++){
    1.49
    onload
    1.48
     불구
    1.48
    POSITIVE LOGITS
    ন
    1.88
    n
    1.73
    inl
    1.69
    in
    1.68
    ראל
    1.66
    ﺪ
    1.61
    ች
    1.58
    त्मक
    1.56
    ﻈ
    1.54
    hetics
    1.54
    Activations Density 0.020%

    No Known Activations