© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9977
    Prev
    Next
    INDEX
    Explanations

    words associated with focusing or concentrating

    oai_token-act-pair · gemini-2.0-flash

    focus concentrate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    twimg
    -0.59
    CodeDom
    -0.59
     дописавши
    -0.57
    Galeria
    -0.57
    explique
    -0.57
    lblNewLabel
    -0.54
    érial
    -0.54
    nake
    -0.52
     Gilman
    -0.52
    ணை
    -0.52
    POSITIVE LOGITS
     focus
    1.63
     Focus
    1.52
    Focus
    1.50
    focus
    1.45
     FOCUS
    1.42
     focusing
    1.38
     Fokus
    1.38
    FOCUS
    1.38
     focuses
    1.37
     focused
    1.31
    Activations Density 0.963%

    No Known Activations