© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9614
    Prev
    Next
    INDEX
    Explanations

    words or phrases that refer to formal definitions, notations, or arguments, especially in a mathematical or technical context

    oai_token-act-pair · gemini-2.0-flash

    mathematical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Elector
    -0.59
    élie
    -0.57
     Orrell
    -0.56
     udaler
    -0.55
     הן
    -0.54
     Schicksal
    -0.54
    cím
    -0.54
     consigo
    -0.54
     Boulogne
    -0.54
     StatefulWidget
    -0.53
    POSITIVE LOGITS
     InputDecoration
    0.68
     дописавши
    0.61
    MessageTagHelper
    0.57
    zarchiwizowane
    0.54
    parsedMessage
    0.52
     disambiguazione
    0.51
    PerformLayout
    0.49
     mouseY
    0.49
    ResumeLayout
    0.47
    around
    0.44
    Activations Density 2.904%

    No Known Activations