© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4496
    Prev
    Next
    INDEX
    Explanations

    scientific and technical vocabulary related to chemical compounds, research methods, and botany, often appearing in academic or research-oriented texts.

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -1.11
     gynhyrchwyd
    -1.05
     pleaſure
    -0.98
     Monfieur
    -0.98
     itſelf
    -0.96
     Biôgrafia
    -0.96
     auffi
    -0.95
     ſta
    -0.94
     myſelf
    -0.94
     Jefus
    -0.93
    POSITIVE LOGITS
    .
    0.79
    :
    0.70
     in
    0.65
     -
    0.54
     II
    0.51
     –
    0.48
     (
    0.47
     as
    0.47
     III
    0.46
    ↵↵↵↵
    0.46
    Activations Density 10.118%

    No Known Activations