© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11716
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to sports competitions and athletes

    oai_token-act-pair · gemini-2.0-flash

    sports championships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ComVisible
    -0.96
     raiſ
    -0.95
     itſelf
    -0.93
    AndEndTag
    -0.92
    MemoryWarning
    -0.92
     becauſe
    -0.90
     whoſe
    -0.90
     pleaſure
    -0.89
     leaſt
    -0.89
    AddTagHelper
    -0.88
    POSITIVE LOGITS
     
    0.56
    必
    0.48
     AR
    0.48
    AM
    0.47
     AM
    0.45
     ar
    0.45
     R
    0.44
     الت
    0.44
    Edit
    0.44
     Ar
    0.44
    Activations Density 1.142%

    No Known Activations