© 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. 5009
    Prev
    Next
    INDEX
    Explanations

    This neuron detects code, mathematics and file paths

    oai_token-act-pair · gemini-2.0-flash

    code/math

    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
     basis
    -1.78
     Basis
    -1.61
    basis
    -1.54
    Basis
    -1.48
     bases
    -1.47
     foundation
    -1.43
     foundations
    -1.30
     Bases
    -1.29
     BASIS
    -1.23
    foundation
    -1.22
    POSITIVE LOGITS
    TagMode
    0.68
     consultato
    0.65
     kasarigan
    0.59
    icitis
    0.55
    avut
    0.53
    \{\\
    0.52
    Спољашње
    0.52
    istoitu
    0.52
     userRepository
    0.52
    matchCondition
    0.52
    Activations Density 1.896%

    No Known Activations