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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6135
    Prev
    Next
    INDEX
    Explanations

    the word "drill" and its variations.

    oai_token-act-pair · gemini-2.0-flash

    drill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     auffi
    -0.94
     crdi
    -0.93
     ſind
    -0.91
    DockStyle
    -0.91
     iſt
    -0.90
     cdti
    -0.87
     westfalen
    -0.85
     pegat
    -0.85
     rodríguez
    -0.85
     cauſe
    -0.85
    POSITIVE LOGITS
    ↵↵
    0.77
     ‘
    0.68
    <eos>
    0.68
     For
    0.64
     To
    0.63
     qu
    0.61
     “
    0.61
    ########.
    0.61
     string
    0.60
     ver
    0.59
    Activations Density 0.643%

    No Known Activations