© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10314
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on different types of markup, including math, programming code, and html

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.89
     onOptions
    -0.74
    ISupport
    -0.74
    RenderAtEndOf
    -0.70
    +#+#
    -0.69
     AssemblyCulture
    -0.69
    fjspx
    -0.67
     typelib
    -0.65
    Abitanti
    -0.65
    rrggbb
    -0.63
    POSITIVE LOGITS
    hline
    0.46
     Gel
    0.40
    ровок
    0.40
      
    0.39
    ędzynarod
    0.38
     uintptr
    0.38
    CLUYE
    0.38
    ajemen
    0.37
    bunya
    0.37
     تب
    0.37
    Activations Density 0.232%

    No Known Activations