© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    uses of the words wonder, imagine, difficult, idea, clear, and certain and other words expressing uncertainty or opinion

    oai_token-act-pair · gemini-2.0-flash

    wondering, imagining

    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
    IMPORTED
    -0.60
    krie
    -0.57
    echa
    -0.50
     chảy
    -0.50
    carea
    -0.48
     single
    -0.47
     load
    -0.46
    load
    -0.45
    országban
    -0.45
    CHARGE
    -0.44
    POSITIVE LOGITS
    <bos>
    0.93
    ConstraintMaker
    0.92
    ArrowToggle
    0.85
     raiſ
    0.72
    SharedCtor
    0.71
     referrerpolicy
    0.69
    Personensuche
    0.63
     kasarigan
    0.63
     itſelf
    0.62
    IUrlHelper
    0.62
    Activations Density 2.115%

    No Known Activations