© 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. 522
    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
    лни
    0.41
    :\
    0.35
    <
    0.34
    localPosition
    0.32
     discontent
    0.31
    வற்றை
    0.30
    \'
    0.30
    的最
    0.30
    _{
    0.29
    MMM
    0.29
    POSITIVE LOGITS
    cosa
    0.38
    kata
    0.34
    ค์
    0.34
     futura
    0.33
    ів
    0.33
     umož
    0.32
    ges
    0.32
     sels
    0.32
    톤
    0.32
    チュラル
    0.31
    Activations Density 1.705%

    No Known Activations