© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8004
    Prev
    Next
    INDEX
    Explanations

    instances of number sequences representing years

    oai_token-act-pair · 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
    -1.88
     Efq
    -1.84
     Majefty
    -1.82
     iſt
    -1.78
     Anſ
    -1.77
     auffi
    -1.76
     ―――――
    -1.74
     Monfieur
    -1.70
     ſche
    -1.70
     ſind
    -1.70
    POSITIVE LOGITS
     
    1.98
    ’
    1.58
    ↵↵
    1.55
    '
    1.51
    <eos>
    1.41
      
    1.37
    <bos>
    1.27
    ↵
    1.22
    .
    1.06
       
    0.98
    Activations Density 1.632%

    No Known Activations