© 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. 4436
    Prev
    Next
    INDEX
    Explanations

    words which are descriptive of the overall quality or state of something.

    oai_token-act-pair · gemini-2.0-flash

    company information

    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
     ivelany
    -0.75
    pexpr
    -0.65
     noqa
    -0.65
    Rüyada
    -0.64
     مرئيه
    -0.64
    TypedDataSet
    -0.63
    XmlType
    -0.61
    phorbia
    -0.61
     насељу
    -0.60
    ANTLR
    -0.60
    POSITIVE LOGITS
     vielmehr
    0.57
     directly
    0.50
     hvad
    0.48
     ordinary
    0.45
    credential
    0.44
     bedste
    0.43
     acercar
    0.43
     known
    0.42
     directamente
    0.42
     BoxDecoration
    0.41
    Activations Density 4.450%

    No Known Activations