© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5365
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and financial processes

    oai_token-act-pair · gemini-2.0-flash

    next

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ThroughAttribute
    -0.99
     חיצוניים
    -0.86
     Houſe
    -0.84
     myſelf
    -0.83
    CloseOperation
    -0.79
     surla
    -0.79
     photolibrary
    -0.78
     ویکی‌پدیای
    -0.77
    thâu
    -0.77
    Vidite
    -0.77
    POSITIVE LOGITS
     next
    1.55
    next
    1.30
     Next
    1.17
    Next
    1.15
     NEXT
    1.01
    NEXT
    0.94
     nächsten
    0.86
     próximo
    0.69
     nästa
    0.69
     nächste
    0.66
    Activations Density 3.627%

    No Known Activations