© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13193
    Prev
    Next
    INDEX
    Explanations

    terms related to astrophysics and astronomy, particularly those involving circumstellar disks, radiation, and star formation

    oai_token-act-pair · gemini-2.0-flash

    disk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    objc
    -0.58
     XCTest
    -0.57
    PerformLayout
    -0.57
    HtmlAttribute
    -0.53
    visiae
    -0.50
    ান
    -0.50
    thand
    -0.50
    UIControlState
    -0.49
     appoint
    -0.48
    twimg
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
     resourceCulture
    0.73
     مشين
    0.68
     فريبيس
    0.63
    ChildScrollView
    0.59
    >[]
    0.58
     åren
    0.57
    <![
    0.57
     médicas
    0.57
    _();
    0.56
    Activations Density 1.484%

    No Known Activations