© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13946
    Prev
    Next
    INDEX
    Explanations

    the word "strain", potentially along with words associated with biological materials or physical forces

    oai_token-act-pair · gemini-2.0-flash

    strain

    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
    Negative Logits
    multer
    -0.82
    bootstrapcdn
    -0.80
    TagMode
    -0.79
    WebElementEntity
    -0.74
    MetaObject
    -0.73
    WEBPACK
    -0.72
    ाहरण
    -0.71
    webElementGuid
    -0.71
    jsxFileName
    -0.71
    ArgsConstructor
    -0.71
    POSITIVE LOGITS
     étoit
    0.81
     auroit
    0.80
     feroit
    0.77
     Nuovo
    0.75
     ainfi
    0.74
     aveug
    0.74
    <bos>
    0.71
     pouvoit
    0.71
     myſelf
    0.71
     avoient
    0.71
    Activations Density 1.281%

    No Known Activations