© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9011
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations dealing with computer graphics, video games, or technology, and also words relating to extremely fast cars

    oai_token-act-pair · gemini-2.0-flash

    setup-related terms and configurations

    np_token-act-pair-logits · gpt-4o-mini

    computer gaming performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GeneratedMessage
    -0.57
    Autore
    -0.54
    ανά
    -0.54
     מוז
    -0.53
    ModelAttribute
    -0.51
    MessageTagHelper
    -0.50
    IntoConstraints
    -0.49
    ConstraintMaker
    -0.49
     Instrumente
    -0.49
    ⓧ
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.63
     setup
    0.55
    TagMode
    0.53
     Taktlose
    0.53
    cu
    0.48
     Setup
    0.48
     SETUP
    0.47
    setup
    0.47
    Rhestr
    0.47
     settings
    0.47
    Activations Density 1.587%

    No Known Activations