© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12628
    Prev
    Next
    INDEX
    Explanations

    words in a paragraph expressing contrasting opinions

    oai_token-act-pair · gemini-2.0-flash

    Black

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Jefus
    -0.94
     Majefty
    -0.91
     myſelf
    -0.88
     Efq
    -0.87
     Monfieur
    -0.86
     themſelves
    -0.79
     uſed
    -0.77
     ſeveral
    -0.76
     houſe
    -0.75
     Chrift
    -0.71
    POSITIVE LOGITS
     black
    1.66
    black
    1.48
     Black
    1.27
    Black
    1.25
     BLACK
    1.21
    BLACK
    1.17
     hitam
    1.06
     blacks
    1.05
    黑
    1.00
    的黑
    0.97
    Activations Density 1.321%

    No Known Activations