© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16247
    Prev
    Next
    INDEX
    Explanations

    This neuron activates for miscellaneous words in French, English, and possibly other languages, without an obvious theme.

    oai_token-act-pair · gemini-2.0-flash

    vais

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    TagMode
    -0.75
     transfieras
    -0.73
     initComponents
    -0.69
    .")]
    -0.64
    complexContent
    -0.63
     cellspacing
    -0.62
    .")
    
    -0.62
    MLLoader
    -0.61
    cheibe
    -0.60
    UnitTesting
    -0.59
    POSITIVE LOGITS
     AssemblyCulture
    0.48
    łys
    0.41
     الرياضيه
    0.41
    properly
    0.41
    most
    0.41
     most
    0.39
    тисти
    0.37
    ترة
    0.37
     kav
    0.36
    📫
    0.35
    Activations Density 0.051%

    No Known Activations