© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 424
    Prev
    Next
    INDEX
    Explanations

    mentions of data, statistics, or percentages in technical writing

    oai_token-act-pair · gemini-2.0-flash

    missing or discard

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IndentedString
    -0.94
     defaultstate
    -0.72
     发表于
    -0.71
     onOptions
    -0.67
    rungsseite
    -0.66
    webElementXpaths
    -0.66
    StoryboardSegue
    -0.65
    ########.
    -0.64
    sizeCache
    -0.63
    /**
    -0.61
    POSITIVE LOGITS
     missing
    0.76
     discard
    0.70
     skip
    0.64
     Discard
    0.64
    missing
    0.64
    Missing
    0.63
     omit
    0.63
     ignore
    0.62
     ignoring
    0.61
     ignor
    0.60
    Activations Density 3.175%

    No Known Activations