© 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. 16279
    Prev
    Next
    INDEX
    Explanations

    code snippets related to assembly language

    oai_token-act-pair · gemini-2.0-flash

    assembly

    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
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.68
     GenerationType
    -0.68
     createState
    -0.59
    InSection
    -0.59
    InstanceState
    -0.57
     numberOfRows
    -0.56
    providedIn
    -0.55
     onlyOwner
    -0.55
    TestingModule
    -0.54
    __":
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
     Савезне
    0.71
     AssemblyCulture
    0.70
    <bos>
    0.67
    Rüyada
    0.63
     חיצוניים
    0.62
     auffi
    0.61
     kasarigan
    0.59
    IUrlHelper
    0.59
    contentLoaded
    0.58
    Activations Density 0.543%

    No Known Activations