© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3672
    Prev
    Next
    INDEX
    Explanations

    the word "doesn't"

    oai_token-act-pair · gemini-2.0-flash

    doesn

    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
    ArgumentParser
    -1.02
    bibfield
    -0.99
    urlpatterns
    -0.94
    :✨
    -0.92
     مشين
    -0.91
    bibinfo
    -0.90
    IntoConstraints
    -0.90
    adaptiveStyles
    -0.90
    ÉM
    -0.89
    __*/
    -0.89
    POSITIVE LOGITS
    <bos>
    1.59
    '
    0.86
    a
    0.76
    (
    0.73
    "
    0.70
    A
    0.64
    S
    0.62
    C
    0.61
    st
    0.58
    is
    0.57
    Activations Density 1.112%

    No Known Activations