© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5045
    Prev
    Next
    INDEX
    Explanations

    phrases used in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    enseits
    -0.58
    ManyToMany
    -0.54
    \"",
    -0.53
    lccn
    -0.50
    latego
    -0.50
    makeConstraints
    -0.50
     المعيارى
    -0.49
    fxml
    -0.49
     disponibilités
    -0.49
    <<<<<<<<
    -0.48
    POSITIVE LOGITS
    ########.
    0.91
    +:+
    0.69
    mstyle
    0.55
     uVar
    0.54
    PRNewswire
    0.53
     venons
    0.52
    ISupport
    0.52
    GEBURTSDATUM
    0.50
    jsxFileName
    0.50
     resourceCulture
    0.50
    Activations Density 12.931%

    No Known Activations