© 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. 6210
    Prev
    Next
    INDEX
    Explanations

    the word "trigger" and related action words such as influence or change

    oai_token-act-pair · gemini-2.0-flash

    trigger

    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
     trigger
    -2.08
    trigger
    -1.91
     triggered
    -1.91
     Trigger
    -1.88
     triggers
    -1.84
    Trigger
    -1.79
     triggering
    -1.78
    <bos>
    -1.62
    triggered
    -1.52
     Triggers
    -1.52
    POSITIVE LOGITS
    DeleteBehavior
    0.81
    setVerticalGroup
    0.78
    ]--;
    0.71
    IntoConstraints
    0.71
    ArgsConstructor
    0.71
    存于互联网档案馆
    0.70
    transQ
    0.69
    mybatisplus
    0.69
     HasFactory
    0.68
    astify
    0.68
    Activations Density 7.023%

    No Known Activations