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. 7288
    Prev
    Next
    INDEX
    Explanations

    the word "mostly" and also has a weak association with the word "however"

    oai_token-act-pair · gemini-2.0-flash

    mostly

    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
     myſelf
    -1.73
     itſelf
    -1.63
     pleaſure
    -1.62
     Efq
    -1.60
     purpoſe
    -1.54
     raiſ
    -1.50
     houſe
    -1.48
     whoſe
    -1.45
     Anſ
    -1.44
     Theſe
    -1.41
    POSITIVE LOGITS
    ↵↵
    0.94
    er
    0.94
    ,
    0.91
     (
    0.91
      
    0.90
    s
    0.86
    e
    0.82
    <eos>
    0.81
     "
    0.81
    .
    0.80
    Activations Density 1.560%

    No Known Activations