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. 7234
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "spirit"

    oai_token-act-pair · gemini-2.0-flash

    spirit

    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
     auroit
    -1.12
     Efq
    -1.09
     avoient
    -1.03
     feroit
    -1.01
     étoient
    -1.00
     pouvoit
    -0.98
     Monfieur
    -0.97
     étoit
    -0.96
     mauva
    -0.89
     eût
    -0.88
    POSITIVE LOGITS
    <bos>
    0.71
     and
    0.61
     for
    0.60
    '
    0.55
     
    0.55
     is
    0.54
     (
    0.52
    <eos>
    0.50
     so
    0.49
    
    0.49
    Activations Density 0.204%

    No Known Activations