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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 700
    Prev
    Next
    INDEX
    Explanations

    text describing legal and regulatory compliance, particularly related to providing timely notice.

    oai_token-act-pair · gemini-2.0-flash

    Warnings and alerts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     alert
    -2.11
     Alert
    -2.06
     notification
    -2.03
     warning
    -1.98
     alerts
    -1.91
     Notice
    -1.89
     notice
    -1.88
     notifications
    -1.87
     Notification
    -1.85
     Warning
    -1.84
    POSITIVE LOGITS
    ıca
    0.45
    mangle
    0.43
     setUsername
    0.41
    ุน
    0.41
     INVENTION
    0.38
    initas
    0.38
     Spalding
    0.37
     sélections
    0.37
    大了
    0.36
     geçen
    0.36
    Activations Density 1.282%

    No Known Activations