© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3059
    Prev
    Next
    INDEX
    Explanations

    words that are technical terms in a number of different fields including hemp farming, marketing, survey, solar power, substance abuse, laser, and medicine

    oai_token-act-pair · gemini-2.0-flash

    Technical and commercial descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     quæ
    -0.66
     récomp
    -0.62
     Theſe
    -0.61
     automatiques
    -0.59
     eorum
    -0.59
     dedans
    -0.58
    collant
    -0.57
     groote
    -0.57
     neceſſ
    -0.56
     ainfi
    -0.56
    POSITIVE LOGITS
     OMIT
    0.81
    TypedDataSet
    0.79
    RenderAtEndOf
    0.78
    LabelTagHelper
    0.77
     GenerationType
    0.75
    Hentet
    0.74
     StatelessWidget
    0.71
     @"/
    0.70
     Vikipedi
    0.69
    DoubleQuotes
    0.69
    Activations Density 4.826%

    No Known Activations