© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    uses of the `operator` keyword in code

    oai_token-act-pair · gemini-2.0-flash

    operator

    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
     invokingState
    -0.70
     BoxFit
    -0.69
     którzy
    -0.65
    rouwen
    -0.63
    LEncoder
    -0.63
     inmiddels
    -0.63
    idescreen
    -0.61
    TintMode
    -0.60
     архивлан
    -0.60
     autorytatywna
    -0.59
    POSITIVE LOGITS
     BEHAV
    0.56
    ing
    0.56
    olen
    0.56
    osph
    0.56
    Jereo
    0.54
    oblo
    0.51
    ING
    0.50
     testo
    0.50
    getDisplay
    0.49
    โล
    0.49
    Activations Density 0.392%

    No Known Activations