© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4477
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and scientific notation, often containing greek letters

    oai_token-act-pair · gemini-2.0-flash

    Mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    NUMX
    -0.69
    MENAFN
    -0.66
    )");
    -0.64
     %\
    -0.57
    adalajara
    -0.56
    %%\
    -0.56
    omeness
    -0.56
    )";
    -0.55
     \
    -0.54
    ſelves
    -0.53
    POSITIVE LOGITS
    bigsqcup
    0.68
    supset
    0.64
    bigcap
    0.61
    sqcup
    0.59
    ddot
    0.57
     that
    0.54
    varrho
    0.53
    windowFixed
    0.52
    triangleq
    0.52
    unistd
    0.51
    Activations Density 4.607%

    No Known Activations