© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16374
    Prev
    Next
    INDEX
    Explanations

    snippets of code, likely C or C++, and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Brackets/quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     оригіналу
    -0.78
     nakalista
    -0.72
    providedIn
    -0.67
     ConstraintSet
    -0.66
     altrimenti
    -0.65
    InjectAttribute
    -0.65
     disambiguazione
    -0.64
    WithIdentifier
    -0.62
    principalTable
    -0.62
     uintptr
    -0.62
    POSITIVE LOGITS
    <bos>
    0.79
    ↵↵
    0.57
    UnknownFields
    0.54
    ↵
    0.52
    <eos>
    0.51
    клопе
    0.49
    thâu
    0.48
    슷
    0.44
    ↵↵↵
    0.43
    ásban
    0.42
    Activations Density 6.273%

    No Known Activations