© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11545
    Prev
    Next
    INDEX
    Explanations

    the word "activated"

    oai_token-act-pair · gemini-2.0-flash

    activated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     activated
    -0.82
     activate
    -0.75
     activation
    -0.75
     activates
    -0.68
    activation
    -0.65
    activated
    -0.63
     useDispatch
    -0.63
    roveň
    -0.63
    }`);
    -0.60
    TNode
    -0.60
    POSITIVE LOGITS
     AssemblyCulture
    1.02
    Geplaatst
    0.90
     SIMBAD
    0.77
    EndGlobalSection
    0.73
     FishBase
    0.69
     INSPIRE
    0.69
    avez
    0.69
     officio
    0.68
    AutoScaleMode
    0.66
     OMIT
    0.64
    Activations Density 0.382%

    No Known Activations