© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12843
    Prev
    Next
    INDEX
    Explanations

    the word "total" or percentages along with "accounting for," often in numerical data.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Total
    -2.77
     total
    -2.73
    Total
    -2.69
    total
    -2.66
     TOTAL
    -2.52
    TOTAL
    -2.48
     totale
    -2.23
     setTotal
    -1.98
     totales
    -1.97
     getTotal
    -1.95
    POSITIVE LOGITS
     grand
    0.56
     AspNetCore
    0.51
     Grand
    0.50
    feira
    0.46
    AnchorStyles
    0.45
    ]){
    0.45
     GRAND
    0.44
    Grand
    0.42
    ArgumentParser
    0.41
    featureID
    0.40
    Activations Density 2.441%

    No Known Activations