© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9360
    Prev
    Next
    INDEX
    Explanations

    words 'functional' or 'function' in the context of programming or mathematics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     المعيارى
    -0.71
    enumi
    -0.58
     كومونز
    -0.57
     Mejía
    -0.57
     FileNotFound
    -0.55
     Recorded
    -0.54
    HomeController
    -0.53
     Eureka
    -0.53
    χεία
    -0.53
    ruptedException
    -0.52
    POSITIVE LOGITS
     function
    1.90
     Function
    1.80
     FUNCTION
    1.68
    Function
    1.64
    function
    1.63
    FUNCTION
    1.63
     functions
    1.59
     fonction
    1.57
     functional
    1.48
     func
    1.48
    Activations Density 0.564%

    No Known Activations