© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12107
    Prev
    Next
    INDEX
    Explanations

    words related to actions, especially rituals, experiments, and physical exertion .

    oai_token-act-pair · gemini-2.0-flash

    perform

    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
     performed
    -2.02
     perform
    -1.92
     performing
    -1.91
     Perform
    -1.79
    Performing
    -1.74
     Performed
    -1.73
    Perform
    -1.70
     performs
    -1.70
    performed
    -1.66
     Performing
    -1.63
    POSITIVE LOGITS
    ChromeDriver
    0.80
    ReusableCell
    0.70
    citep
    0.62
    omitempty
    0.59
    MLLoader
    0.57
    gemaakt
    0.57
    +#+#
    0.56
    JpaRepository
    0.56
     متعلقه
    0.55
    setof
    0.54
    Activations Density 4.441%

    No Known Activations