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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11819
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on various elements of coding and language-related text, including angle brackets, quotation marks, and some common programming terms.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegistryLite
    -0.84
    Vidite
    -0.82
    ReusableCell
    -0.81
    kháu
    -0.78
    MigrationBuilder
    -0.77
    CppCodeGen
    -0.76
    цездатний
    -0.75
    تقاوى
    -0.74
    
    -0.73
    expandindo
    -0.73
    POSITIVE LOGITS
    aume
    0.48
    chatId
    0.46
     direction
    0.46
    acons
    0.45
     scene
    0.44
    eche
    0.44
    Swal
    0.43
     percent
    0.43
    пенно
    0.43
     corresponding
    0.42
    Activations Density 3.415%

    No Known Activations