© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13664
    Prev
    Next
    INDEX
    Explanations

    narrative text with dates and references to cold weather, war, and death

    oai_token-act-pair · gemini-2.0-flash

    winter-related terms

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

    winter

    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
    SharedDtor
    -0.70
    addContainerGap
    -0.69
    ValueGeneration
    -0.63
     @"/
    -0.62
    存于互联网档案馆
    -0.59
    awtextra
    -0.55
    WriteTagHelper
    -0.54
    verwijspagina
    -0.54
    msgSender
    -0.52
    Források
    -0.52
    POSITIVE LOGITS
     winter
    1.24
    winter
    1.03
     Winter
    1.02
    Winter
    0.99
     WINTER
    0.94
     winters
    0.93
    WINTER
    0.85
     invierno
    0.80
    冬
    0.77
     vinter
    0.75
    Activations Density 1.707%

    No Known Activations