© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3315
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated words in different languages, possibly in informal or broken language.

    oai_token-act-pair · gemini-2.0-flash

    code and data 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_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
     toast
    -0.43
    hability
    -0.39
    expandindo
    -0.39
     Baños
    -0.39
     Bunga
    -0.38
    phorus
    -0.38
    มาย
    -0.38
    seers
    -0.38
     nemo
    -0.37
    PreferredItem
    -0.37
    POSITIVE LOGITS
    TypedDataSet
    0.78
    tidaknya
    0.77
     ویکی‌پدیا
    0.69
     nahilalakip
    0.66
     löyty
    0.64
     estimés
    0.64
    Tembelea
    0.63
    Попис
    0.62
    JoinColumn
    0.62
    CppMethod
    0.62
    Activations Density 0.948%

    No Known Activations