© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4935
    Prev
    Next
    INDEX
    Explanations

    HTML formatting tags and quotes

    oai_token-act-pair · gemini-2.0-flash

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -1.07
    IndentedString
    -0.79
    Datuak
    -0.75
     ExecuteAsync
    -0.72
     EconPapers
    -0.69
    MENAFN
    -0.65
     autorytatywna
    -0.65
    ImageContext
    -0.64
    awtextra
    -0.63
    twimg
    -0.62
    POSITIVE LOGITS
     credere
    0.51
     tfsi
    0.50
     român
    0.50
    ModelForm
    0.47
     professionale
    0.46
     plă
    0.46
    estä
    0.45
     pagare
    0.45
     bibl
    0.45
     îng
    0.44
    Activations Density 0.957%

    No Known Activations