© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11871
    Prev
    Next
    INDEX
    Explanations

    references to military or sports team leadership positions

    oai_token-act-pair · gemini-2.0-flash

    captain

    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
    <bos>
    -2.19
    '
    -0.59
    ’
    -0.54
     the
    -0.52
     captain
    -0.51
     and
    -0.49
    省市镇
    -0.48
     are
    -0.47
    Captain
    -0.45
     con
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.66
    __*/
    0.63
    fromnode
    0.63
     Wayback
    0.63
     yachts
    0.62
     Mitochond
    0.62
     impea
    0.61
     rhubarb
    0.61
     auber
    0.59
     GetEnumerator
    0.58
    Activations Density 0.321%

    No Known Activations