© 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. 680
    Prev
    Next
    INDEX
    Explanations

    math typesetting, especially matrices and other notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    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
     ""));
    -0.51
     consultato
    -0.48
    ()))
    -0.46
    ComponentModel
    -0.45
    yw
    -0.45
     дово
    -0.43
    Hozzáférés
    -0.43
    dostęp
    -0.43
    gars
    -0.43
    ))
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.74
    Demografie
    0.73
    WriteBarrier
    0.71
    ArrowToggle
    0.70
     Numerade
    0.68
    SharedDtor
    0.66
    المكان
    0.65
    PerformLayout
    0.65
    nictví
    0.64
     Winaray
    0.64
    Activations Density 6.484%

    No Known Activations