© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6602
    Prev
    Next
    INDEX
    Explanations

    The neuron identifies the word "leading" and words associated with groups (team or prevalent).

    oai_token-act-pair · gemini-2.0-flash

    leading

    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
     leading
    -2.45
    Leading
    -2.27
    leading
    -2.17
     Leading
    -2.16
    <bos>
    -2.03
    LEADING
    -1.58
     leads
    -1.31
     füh
    -1.30
     веду
    -1.15
     lead
    -1.12
    POSITIVE LOGITS
    alini
    0.53
     martyrdom
    0.53
    
    0.52
     tkinter
    0.51
    itarian
    0.47
    Etimología
    0.46
    sdl
    0.45
    openqa
    0.45
     Acceptance
    0.45
    setColumn
    0.45
    Activations Density 1.262%

    No Known Activations