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. 7173
    Prev
    Next
    INDEX
    Explanations

    the word "due", and also names

    oai_token-act-pair · gemini-2.0-flash

    due

    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
     
    -1.33
      
    -1.20
    ↵
    -1.02
     (
    -0.96
       
    -0.91
    _
    -0.90
     I
    -0.90
    ↵↵
    -0.88
    :
    -0.85
    <eos>
    -0.84
    POSITIVE LOGITS
     Majefty
    1.97
     myſelf
    1.95
     Efq
    1.82
     purpoſe
    1.80
     itſelf
    1.75
     Jefus
    1.72
     pleaſure
    1.70
     himſelf
    1.66
    ſelf
    1.63
     themſelves
    1.62
    Activations Density 0.880%

    No Known Activations