© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    debugging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
    elige
    2.58
    ார
    2.47
    ش
    2.47
     ''){
    2.43
     Archivlink
    2.41
    rer
    2.38
    𝐚
    2.37
    grado
    2.35
    見える
    2.35
    nde
    2.32
    POSITIVE LOGITS
    ১
    2.74
    ാം
    2.65
     minded
    2.65
    
    2.54
    ر
    2.53
    ট
    2.48
    𝑛
    2.48
    อะคาเดมี
    2.43
    
    2.42
     rainy
    2.40
    Activations Density 0.067%

    No Known Activations