© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10897
    Prev
    Next
    INDEX
    Explanations

    descriptions of playing poker

    oai_token-act-pair · gemini-2.0-flash

    Games and winning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HandlerContext
    -0.75
     ElementRef
    -0.66
    PerformLayout
    -0.65
    ViewImports
    -0.62
    AutoresizingMask
    -0.60
     BoxDecoration
    -0.59
     Waray
    -0.58
    ferrer
    -0.56
     arşivlendi
    -0.56
     WaitForSeconds
    -0.56
    POSITIVE LOGITS
     reaſon
    0.53
     pleaſure
    0.52
     tranſ
    0.51
     հղումներ
    0.50
     uſed
    0.50
     ſmall
    0.50
     itſelf
    0.50
    zunehmen
    0.49
    CORD
    0.49
     becauſe
    0.47
    Activations Density 0.275%

    No Known Activations