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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13564
    Prev
    Next
    INDEX
    Explanations

    code blocks, perhaps C or C++, including the main function, curly braces, parentheses, and newlines

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    np_max-act · 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
    <bos>
    -0.64
    TabIndex
    -0.53
    zal
    -0.50
    WireFormat
    -0.50
    πω
    -0.50
    :✨
    -0.49
    зда
    -0.48
     Scalars
    -0.48
    kha
    -0.47
    exitRule
    -0.47
    POSITIVE LOGITS
    kuuta
    0.49
    endpush
    0.45
     Efq
    0.44
    슷
    0.43
     başına
    0.41
     extranjera
    0.41
     åp
    0.40
    ünkü
    0.40
     asiática
    0.40
     jButton
    0.40
    Activations Density 0.139%

    No Known Activations