© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6765
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on technical language, whether code or mathematical formulas, and also on words related to arrangements/combinations.

    oai_token-act-pair · gemini-2.0-flash

    Combinations and variations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    InjectAttribute
    -0.75
    IBOutlet
    -0.73
    IntoConstraints
    -0.66
    DataAnnotations
    -0.65
    BeginContext
    -0.63
    ConstraintMaker
    -0.62
    InstrumentedTest
    -0.62
    IndentedString
    -0.60
     հղումներ
    -0.60
    WebpackPlugin
    -0.60
    POSITIVE LOGITS
     combinations
    1.28
     variations
    1.27
     variation
    1.23
     Combinations
    1.09
     variants
    1.09
     permutations
    1.08
    variations
    1.06
     variant
    1.04
     combination
    1.04
    variation
    1.02
    Activations Density 2.893%

    No Known Activations