© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    instances of actions having "take" as a component

    oai_token-act-pair · 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
    migrationBuilder
    -0.84
    MemoryWarning
    -0.72
    Koordinaten
    -0.71
    jfree
    -0.67
    ureka
    -0.63
    XmlAccessType
    -0.62
    +};
    -0.59
    umblr
    -0.59
    Storyboard
    -0.59
    Revenir
    -0.58
    POSITIVE LOGITS
    contentLoaded
    0.61
    ContentAsync
    0.57
    Бахар
    0.54
    ArrowToggle
    0.52
    ην
    0.50
    afficheront
    0.50
    saraba
    0.49
    AccessorTable
    0.48
     OTO
    0.47
    ंदीखरीदारी
    0.46
    Activations Density 5.914%

    No Known Activations