© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12972
    Prev
    Next
    INDEX
    Explanations

    the word "the" and text related to highways and road systems

    oai_token-act-pair · gemini-2.0-flash

    say "line"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IUrlHelper
    -0.69
     kasarigan
    -0.68
     ujednoznacz
    -0.58
     cherchés
    -0.57
     useStyles
    -0.56
    зулта
    -0.56
    Slf
    -0.52
     nahilalakip
    -0.52
    cellaneous
    -0.51
    ReusableCell
    -0.50
    POSITIVE LOGITS
     line
    2.38
     Line
    2.06
     lines
    1.97
    line
    1.93
    Line
    1.89
     LINE
    1.81
     Lines
    1.75
    lines
    1.69
    LINE
    1.66
    Lines
    1.57
    Activations Density 3.682%

    No Known Activations