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. 16236
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations and their founding

    oai_token-act-pair · gemini-2.0-flash

    existence

    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
     Bonnet
    -0.54
    FormState
    -0.53
    wohnt
    -0.52
     Cheval
    -0.49
    chromedriver
    -0.46
     getService
    -0.46
    ofas
    -0.45
     wedge
    -0.44
     attending
    -0.44
     NDEBUG
    -0.44
    POSITIVE LOGITS
     existed
    1.08
     exists
    1.04
     exist
    1.01
     existence
    0.88
    exists
    0.87
     existi
    0.86
     EXIST
    0.85
     Exist
    0.79
     Exists
    0.79
     existir
    0.76
    Activations Density 2.297%

    No Known Activations