© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13011
    Prev
    Next
    INDEX
    Explanations

    many different numbers, percentages, and mathematical units of measure

    oai_token-act-pair · gemini-2.0-flash

    sentence contrast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     while
    -2.78
    while
    -2.66
     While
    -2.33
     WHILE
    -2.28
    While
    -2.28
     mentre
    -2.28
    WHILE
    -2.19
     mientras
    -2.17
     enquanto
    -2.16
     whilst
    -2.13
    POSITIVE LOGITS
    ,
    0.47
    idis
    0.46
    架
    0.44
    orap
    0.42
    าร
    0.41
    Paz
    0.39
    lede
    0.39
    кову
    0.39
    мба
    0.38
    功
    0.38
    Activations Density 1.463%

    No Known Activations