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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12734
    Prev
    Next
    INDEX
    Explanations

    words or phrases used in arguments or discussions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ?,?,
    -0.50
    aarrggbb
    -0.47
     
    -0.46
    endenza
    -0.43
    MemoryWarning
    -0.43
     s
    -0.43
     however
    -0.42
    ign
    -0.42
     keyPressed
    -0.42
    ajemen
    -0.41
    POSITIVE LOGITS
     ſeveral
    0.77
     Majefty
    0.75
     houſe
    0.75
     whoſe
    0.74
     Houſe
    0.73
     itſelf
    0.73
     himſelf
    0.72
     themſelves
    0.72
     theſe
    0.72
     perſon
    0.71
    Activations Density 5.042%

    No Known Activations