© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5603
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "op", likely short for "operation"

    oai_token-act-pair · gemini-2.0-flash

    op

    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
    op
    -0.68
    ing
    -0.59
    yi
    -0.58
    ци
    -0.56
     op
    -0.56
    i
    -0.54
    di
    -0.52
    ey
    -0.51
    ti
    -0.50
    iti
    -0.50
    POSITIVE LOGITS
     ExecuteAsync
    1.10
    TagMode
    0.90
    harusnya
    0.84
     <<<<<<<<<<<<<<
    0.84
    setVerticalGroup
    0.82
    
    0.82
    ftagPool
    0.81
     GenerationType
    0.81
     المعيارى
    0.80
     FetchType
    0.78
    Activations Density 0.679%

    No Known Activations