© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1265
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and phrases indicative of sports reporting

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WaitGroup
    -0.67
     createState
    -0.49
    ViewInit
    -0.49
     发表于
    -0.47
    躇
    -0.46
    steamcommunity
    -0.46
     invokingState
    -0.46
    lccn
    -0.46
     Quell
    -0.45
    pixabay
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.78
    Personendaten
    0.75
     OMITBAD
    0.69
    Enllaces
    0.59
     CreateTagHelper
    0.59
     Roskov
    0.59
    RuleContext
    0.57
    setVerticalGroup
    0.57
    ValueGenerated
    0.53
    alnız
    0.52
    Activations Density 1.294%

    No Known Activations