© 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. 8780
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to legal issues, particularly within a correctional context, but also related to identity and finance

    oai_token-act-pair · gemini-2.0-flash

    customer service interactions

    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
    Bibliografia
    -0.52
    fortawesome
    -0.43
    Lear
    -0.43
    Works
    -0.43
     विश्वसनीयता
    -0.42
    si
    -0.42
     taip
    -0.42
     Works
    -0.41
    Przypisy
    -0.41
    Conclusion
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.82
    Geplaatst
    0.79
     Мексичка
    0.75
    GenerationType
    0.72
    UnusedPrivate
    0.71
     fubject
    0.69
     للاسماء
    0.66
     >=",
    0.66
     Roskov
    0.64
     المعيارى
    0.63
    Activations Density 17.465%

    No Known Activations