© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13188
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decade"

    oai_token-act-pair · gemini-2.0-flash

    decade

    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
     ―――――
    -1.50
     itſelf
    -1.45
     ་་
    -1.44
     Efq
    -1.41
     themſelves
    -1.40
     myſelf
    -1.34
     Anſ
    -1.33
     ſind
    -1.30
     Majefty
    -1.30
     becauſe
    -1.27
    POSITIVE LOGITS
    ↵↵
    0.99
     
    0.94
    ↵
    0.91
     I
    0.85
     the
    0.83
     The
    0.82
      
    0.77
     a
    0.77
    <eos>
    0.76
     (
    0.73
    Activations Density 0.985%

    No Known Activations