© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5489
    Prev
    Next
    INDEX
    Explanations

    dates and names of people or organizations

    oai_token-act-pair · gemini-2.0-flash

    month names or dates

    np_token-act-pair-logits · gpt-4o-mini

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ,
    -0.69
     للمعارف
    -0.67
     giapp
    -0.59
    IndentedString
    -0.58
    MetaType
    -0.56
    InjectAttribute
    -0.55
    IsContent
    -0.55
    ImageContext
    -0.54
     ddelweddau
    -0.53
    StoreMessageInfo
    -0.52
    POSITIVE LOGITS
    %")
    0.62
     August
    0.60
     May
    0.59
    ignty
    0.58
     March
    0.57
     ")[
    0.57
    "]);
    0.57
     Rosenthal
    0.56
    ()");
    0.56
     October
    0.55
    Activations Density 15.307%

    No Known Activations