© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13589
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and equation-related words, especially in the context of scientific or technical documents.

    oai_token-act-pair · 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
     N
    -1.34
    N
    -1.16
    Ｎ
    -0.87
    Ns
    -0.85
     Ν
    -0.79
     Ns
    -0.79
    𝑁
    -0.77
    NN
    -0.73
    iN
    -0.72
     Nu
    -0.71
    POSITIVE LOGITS
    RegressionTest
    0.85
    مصادر
    0.68
    n
    0.62
     n
    0.56
    RUnlock
    0.56
     Italijanski
    0.53
    note
    0.48
    nom
    0.47
     chỉnh
    0.47
    nz
    0.47
    Activations Density 12.954%

    No Known Activations