© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4436
    Prev
    Next
    INDEX
    Explanations

    the keyword "async"

    oai_token-act-pair · gemini-2.0-flash

    async

    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
     createSprite
    -0.75
    SourceChecksum
    -0.75
    JspWriter
    -0.73
    bootstrapcdn
    -0.73
     betweenstory
    -0.69
    StoryboardSegue
    -0.69
     وتسجيلات
    -0.68
    ɵɵ
    -0.66
    mapStateToProps
    -0.65
     kasarigan
    -0.65
    POSITIVE LOGITS
    UMBUS
    0.50
     Insee
    0.48
     Ptolemy
    0.46
    вь
    0.46
    ATURE
    0.42
     AUSTIN
    0.41
    tagHelperRunner
    0.39
    ouwen
    0.39
    arı
    0.39
    hassee
    0.37
    Activations Density 0.434%

    No Known Activations