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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9623
    Prev
    Next
    INDEX
    Explanations

    the article "a" when it occurs next to capitalization or numbers

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Económica
    -0.69
    ⎩
    -0.66
     Kettle
    -0.66
    phazard
    -0.66
    +#+#
    -0.65
    fromnode
    -0.63
    hình
    -0.62
    Portale
    -0.61
    icator
    -0.60
    OGO
    -0.60
    POSITIVE LOGITS
    <bos>
    2.16
    The
    0.68
    '
    0.64
    '))
    0.57
     The
    0.56
     AssemblyTitle
    0.56
    -
    0.55
    An
    0.54
    ).)
    0.53
    ’
    0.52
    Activations Density 0.434%

    No Known Activations