Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14596
    Prev
    Next
    INDEX
    Explanations

    words related to social gatherings and entertainment events

    oai_token-act-pair · gemini-2.0-flash

    put

    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
    
    -0.69
     محفوظة
    -0.68
    CloseOperation
    -0.65
     Superhost
    -0.64
    makeConstraints
    -0.64
    amental
    -0.63
    complexContent
    -0.62
     Theſe
    -0.61
     Monfieur
    -0.61
    continence
    -0.60
    POSITIVE LOGITS
     put
    0.66
     oprot
    0.65
     production
    0.54
    put
    0.53
    Put
    0.52
     produite
    0.51
     Put
    0.50
    CodeAttribute
    0.49
     produit
    0.47
     puts
    0.46
    Activations Density 1.087%

    No Known Activations