© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    named entities (countries, people, organizations) in the context of conflict and political statements.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    بوابة
    -0.50
    Yourself
    -0.49
    achelor
    -0.48
     Puedes
    -0.47
     Arrangement
    -0.46
    yorsunuz
    -0.45
    inaw
    -0.45
    Application
    -0.45
    Copied
    -0.43
     COMPONENT
    -0.43
    POSITIVE LOGITS
     ويكيميديا
    0.65
    contentLoaded
    0.59
    сылкі
    0.58
    ImageContext
    0.58
     initComponents
    0.57
     WaitForSeconds
    0.57
    NameInMap
    0.57
    msgTypes
    0.56
    WebServlet
    0.56
    "}")
    0.56
    Activations Density 5.988%

    No Known Activations