© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5031
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics notation and language, including symbols, equations, and specific terms

    oai_token-act-pair · gemini-2.0-flash

    physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    CodeAttribute
    -0.58
     chng
    -0.50
    ällor
    -0.50
     аса
    -0.49
    Specificity
    -0.49
    出版年
    -0.46
    Khi
    -0.46
    ames
    -0.45
    len
    -0.45
    irical
    -0.45
    POSITIVE LOGITS
    ()?;
    0.54
    UnusedPrivate
    0.52
    ArrowToggle
    0.50
    achal
    0.50
     Houſe
    0.50
    OGND
    0.50
    drawal
    0.49
    dAtA
    0.49
     yii
    0.49
     تانيه
    0.49
    Activations Density 3.924%

    No Known Activations