© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11913
    Prev
    Next
    INDEX
    Explanations

    words related to sports, medicine, and cooking measurements

    oai_token-act-pair · gemini-2.0-flash

    cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     cup
    -1.34
     Cup
    -1.28
    Cup
    -1.20
     Cups
    -1.20
    cup
    -1.20
     CUP
    -1.09
     cups
    -1.09
    cups
    -0.97
    CUP
    -0.93
    カップ
    -0.77
    POSITIVE LOGITS
     plonge
    0.47
     alimentaire
    0.47
     goutte
    0.47
     inoxydable
    0.46
    LBL
    0.43
    czaj
    0.43
    ruik
    0.42
     Gabb
    0.42
    endforeach
    0.42
    下载附件
    0.42
    Activations Density 8.035%

    No Known Activations