© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    the word "at", especially at the start of a line

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Roskov
    -0.87
     At
    -0.84
    At
    -0.83
    onOptions
    -0.74
    parsedMessage
    -0.73
     defStyle
    -0.72
    انيف
    -0.69
     betweenstory
    -0.68
    ंदीखरीदारी
    -0.68
    hability
    -0.68
    POSITIVE LOGITS
    <bos>
    1.47
    '
    0.64
     when
    0.51
    ’
    0.51
     needing
    0.46
    øre
    0.46
    ूरत
    0.45
     tunn
    0.44
    when
    0.43
    ↵↵
    0.42
    Activations Density 1.491%

    No Known Activations