© 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. 9992
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a wide variety of words, but perhaps is looking for scientific language

    oai_token-act-pair · gemini-2.0-flash

    atoms and energy

    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
     Drugs
    -0.79
    Genes
    -0.78
     Cells
    -0.77
    Cells
    -0.77
     particles
    -0.77
     Words
    -0.76
    Bricks
    -0.76
    words
    -0.76
     bricks
    -0.76
     cells
    -0.76
    POSITIVE LOGITS
     تضيفلها
    0.57
    verwijspagina
    0.54
    queryInterface
    0.52
    initializeApp
    0.51
     BoxFit
    0.50
     nahilalakip
    0.50
    Bism
    0.49
    ModelBuilder
    0.49
    adze
    0.47
    Jereo
    0.46
    Activations Density 5.364%

    No Known Activations