© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    words related to the ozone layer and its depletion

    oai_token-act-pair · gemini-2.0-flash

    ozone layer, UV radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ChildScrollView
    -1.07
     propOrder
    -0.72
    KommentareTeilen
    -0.68
     uintptr
    -0.65
    TagMode
    -0.63
     للاسماء
    -0.62
    IntoConstraints
    -0.62
    PerformLayout
    -0.62
     تضيفلها
    -0.61
     Overflow
    -0.60
    POSITIVE LOGITS
    enumi
    0.50
     ${({
    0.46
     step
    0.43
     ويكي
    0.42
    step
    0.42
    ステップ
    0.42
     bước
    0.42
    stackrel
    0.41
     use
    0.41
    Comté
    0.40
    Activations Density 1.973%

    No Known Activations