© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6128
    Prev
    Next
    INDEX
    Explanations

    mentions of Hong Kong, Universities, British places, food and broadcasting

    oai_token-act-pair · gemini-2.0-flash

    Kong

    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
     تانيه
    -0.97
    .}(
    -0.87
     }}$}
    -0.87
     الحره
    -0.83
     فريبيس
    -0.82
    CloseOperation
    -0.81
    󠁢
    -0.80
    ритори
    -0.80
     简谱
    -0.79
    ...";
    -0.79
    POSITIVE LOGITS
    <bos>
    1.48
    ↵↵
    1.21
    '
    0.94
    ↵
    0.88
     
    0.73
    s
    0.70
    ‘
    0.67
      
    0.66
    <strong>
    0.65
    "
    0.65
    Activations Density 1.018%

    No Known Activations