© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9380
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes, especially the "id" and "data-" attributes

    oai_token-act-pair · gemini-2.0-flash

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     id
    -1.18
     propOrder
    -0.84
    featureID
    -0.82
     typelib
    -0.79
     Audiodateien
    -0.78
    RegressionTest
    -0.71
     дописавши
    -0.71
    MENAFN
    -0.71
     Id
    -0.67
    archiviato
    -0.66
    POSITIVE LOGITS
    ::$
    0.49
    copg
    0.45
    ovács
    0.42
     nuclé
    0.42
     useStyles
    0.42
     anúncio
    0.41
     menar
    0.39
    AfterClass
    0.39
    succeeded
    0.39
     зажига
    0.37
    Activations Density 0.764%

    No Known Activations