© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11330
    Prev
    Next
    INDEX
    Explanations

    phrases involving two distinct things, often in a contrasting capacity

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    -0.74
     Monfieur
    -0.73
     vœux
    -0.71
     myſelf
    -0.69
     للاسماء
    -0.68
     Majefty
    -0.68
     Efq
    -0.68
     ſmall
    -0.67
     themſelves
    -0.66
     purpoſe
    -0.65
    POSITIVE LOGITS
     two
    1.49
    two
    1.17
     Two
    1.09
    Two
    1.05
     deux
    1.03
    TWO
    0.96
     TWO
    0.96
     zwei
    0.94
     beiden
    0.91
     duas
    0.87
    Activations Density 2.304%

    No Known Activations