© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6359
    Prev
    Next
    INDEX
    Explanations

    the word "charge", the word "chart", or names of people, especially the name "Charles."

    oai_token-act-pair · gemini-2.0-flash

    charge/chart

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    uría
    -0.54
     تانيه
    -0.53
    werth
    -0.53
    BarChart
    -0.52
    chart
    -0.52
     springfox
    -0.52
    rhosis
    -0.51
    onucleotide
    -0.50
    EXPR
    -0.50
     strconv
    -0.50
    POSITIVE LOGITS
     QName
    0.60
     iprot
    0.57
    IsInitialized
    0.56
    yntaxException
    0.52
    URLException
    0.52
    istik
    0.51
    AccessFile
    0.49
     Seeder
    0.47
    posedge
    0.47
     الحره
    0.47
    Activations Density 1.653%

    No Known Activations