© 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. 8263
    Prev
    Next
    INDEX
    Explanations

    a mix of the word "pose", words that start with "tu" followed by at most two characters, and single digit numbers

    oai_token-act-pair · gemini-2.0-flash

    pose

    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
    rrggbb
    -1.17
    UserScript
    -1.07
    MLLoader
    -0.98
     resourceCulture
    -0.96
     contextLoads
    -0.96
     <<<<<<<<<<<<<<
    -0.91
     onCreateView
    -0.91
     autorytatywna
    -0.89
     BeautifulSoup
    -0.89
    featureID
    -0.88
    POSITIVE LOGITS
     
    0.63
     and
    0.56
      
    0.55
    </em>
    0.55
     zatem
    0.54
     “
    0.53
     take
    0.53
     one
    0.53
     new
    0.52
    <eos>
    0.51
    Activations Density 3.182%

    No Known Activations