© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    code snippets of various programming languages

    oai_token-act-pair · gemini-2.0-flash

    code and/or equations

    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
    Negative Logits
     $_"
    -0.63
    )";
    -0.61
    )");
    -0.60
    !")
    -0.58
     (\<
    -0.57
    ).
    -0.57
     Efq
    -0.56
    )”.
    -0.54
     ――――
    -0.52
    substack
    -0.52
    POSITIVE LOGITS
    __*/
    0.83
    Personendaten
    0.69
    Legături
    0.66
    :✨
    0.66
    GEBURTSDATUM
    0.65
    QMetaType
    0.63
    esModule
    0.63
    تقاوى
    0.60
    expandindo
    0.59
     AssemblyProduct
    0.55
    Activations Density 2.309%

    No Known Activations