© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9945
    Prev
    Next
    INDEX
    Explanations

    the word 'curve', sometimes in the plural

    oai_token-act-pair · gemini-2.0-flash

    curve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     acres
    -0.94
     acre
    -0.91
     miles
    -0.91
     MaterialApp
    -0.81
     Outlet
    -0.81
     Acre
    -0.77
    InteropServices
    -0.76
    enderror
    -0.75
     mile
    -0.74
     pounds
    -0.72
    POSITIVE LOGITS
    <bos>
    1.51
    ’
    0.60
    '
    0.57
    “
    0.53
    <h2>
    0.52
    (
    0.51
    The
    0.48
     the
    0.47
    So
    0.46
    We
    0.45
    Activations Density 0.915%

    No Known Activations