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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3340
    Prev
    Next
    INDEX
    Explanations

    C++ code, especially include statements and namespace declarations

    oai_token-act-pair · gemini-2.0-flash

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     дописавши
    -0.86
    queryInterface
    -0.81
     समीक्षाओं
    -0.78
     mergeFrom
    -0.77
    inerja
    -0.75
    Grüsse
    -0.75
    Autoritní
    -0.74
     endfor
    -0.72
    pozdrawiam
    -0.72
     conceivably
    -0.71
    POSITIVE LOGITS
    ↵
    0.73
    .~(\
    0.66
    <h2>
    0.65
    ​
    0.58
    <b>
    0.57
    <i>
    0.57
    ("")]
    0.55
    ERS
    0.54
     
    0.53
    rd
    0.52
    Activations Density 0.342%

    No Known Activations