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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7290
    Prev
    Next
    INDEX
    Explanations

    words related to legal and technical language in various languages, possibly related to political treaties, software development, and internet usage

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     tramonto
    -1.68
     nemico
    -1.53
     cervello
    -1.52
     feroit
    -1.52
     avoient
    -1.49
     frattempo
    -1.49
     medesimo
    -1.48
     pescoço
    -1.48
     silenzio
    -1.47
     mourut
    -1.46
    POSITIVE LOGITS
     volume
    0.92
     puro
    0.89
     compro
    0.84
     canon
    0.83
     capital
    0.80
    Климат
    0.80
     canto
    0.79
     final
    0.78
     interval
    0.77
     raso
    0.77
    Activations Density 0.695%

    No Known Activations