© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2551
    Prev
    Next
    INDEX
    Explanations

    this neuron looks for instances of numerical data, ratios, percentages, scores or high scoring words.

    oai_token-act-pair · gemini-2.0-flash

    plans

    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
    cells
    -0.84
    Cells
    -0.80
    nodes
    -0.79
     Stars
    -0.78
     seats
    -0.77
     Cells
    -0.77
     cells
    -0.76
     Nodes
    -0.76
    Nodes
    -0.76
     nodes
    -0.76
    POSITIVE LOGITS
    Schedules
    0.68
     schedules
    0.68
     diets
    0.62
     agendas
    0.61
     budgets
    0.61
     regimens
    0.60
     Schedules
    0.58
     formats
    0.58
     lifestyles
    0.57
     inventories
    0.56
    Activations Density 22.165%

    No Known Activations