© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4128
    Prev
    Next
    INDEX
    Explanations

    mathematical notation in scientific text

    oai_token-act-pair · gemini-2.0-flash

    Math/scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.61
    ...
    -0.57
    ­
    -0.54
    f
    -0.54
    F
    -0.52
    T
    -0.51
    E
    -0.50
    The
    -0.50
    B
    -0.49
    A
    -0.49
    POSITIVE LOGITS
    PerformLayout
    0.95
     quelcon
    0.92
    ergies
    0.91
    ]--;
    0.91
     poupée
    0.88
     pouvoit
    0.85
    PositiveButton
    0.85
    вгений
    0.84
    PERTIES
    0.84
    rungsseite
    0.84
    Activations Density 3.530%

    No Known Activations