© 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. 12208
    Prev
    Next
    INDEX
    Explanations

    javascript code imports and component syntax

    oai_token-act-pair · gemini-2.0-flash

    from

    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
    ArgsConstructor
    -0.66
     alike
    -0.64
     fidélité
    -0.63
     sonno
    -0.63
    èdia
    -0.63
    temos
    -0.63
    manship
    -0.60
     détruit
    -0.58
     coupable
    -0.58
     âgé
    -0.58
    POSITIVE LOGITS
     CreateTagHelper
    0.63
    GOTREF
    0.62
    <bos>
    0.61
    #
    0.58
    addCriterion
    0.57
    MENAFN
    0.56
    consulté
    0.56
     发表于
    0.55
    InjectAttribute
    0.54
    RegressionTest
    0.52
    Activations Density 25.492%

    No Known Activations