© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    the word "bulk," sometimes in the context of surfaces or comparison

    oai_token-act-pair · gemini-2.0-flash

    bulk

    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
    Negative Logits
     gynhyrchwyd
    -0.83
     initComponents
    -0.74
    Autoritní
    -0.71
    MLLoader
    -0.71
    <bos>
    -0.71
     ویکی‌پدیا
    -0.69
    OGND
    -0.68
    Personensuche
    -0.64
     Normdatei
    -0.64
     Bulk
    -0.62
    POSITIVE LOGITS
    expiresIn
    0.55
    "]);
    0.54
    Worth
    0.53
    ]))
    0.52
     Worth
    0.52
    haustible
    0.51
    WORTH
    0.50
     Benav
    0.50
     WORTH
    0.49
    eip
    0.49
    Activations Density 0.390%

    No Known Activations