© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3466
    Prev
    Next
    INDEX
    Explanations

    the word "every"

    np_token-act-pair-logits · gpt-4o-mini

    phrases about money and the value of things

    oai_token-act-pair · gemini-2.0-flash

    every

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mybatisplus
    -0.49
    ABUL
    -0.44
    ISupport
    -0.44
     BrowserModule
    -0.43
    тивным
    -0.42
    깥
    -0.40
    MessageTagHelper
    -0.39
    untitled
    -0.39
    JspWriter
    -0.38
    rovnik
    -0.38
    POSITIVE LOGITS
     every
    3.38
    every
    3.08
    Every
    2.77
     Every
    2.75
     EVERY
    2.25
     ogni
    2.20
     setiap
    2.14
    EVERY
    2.02
    Ogni
    1.95
     chaque
    1.93
    Activations Density 1.753%

    No Known Activations