© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1496
    Prev
    Next
    INDEX
    Explanations

    words related to the legal system

    oai_token-act-pair · gemini-2.0-flash

    judicial system, courts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.54
    ǐ
    -0.52
    kloped
    -0.50
    RegressionTest
    -0.47
    gla
    -0.45
    g
    -0.45
    بيرة
    -0.44
    si
    -0.43
    unmodifiable
    -0.42
     spots
    -0.42
    POSITIVE LOGITS
     Efq
    0.83
    RenderAtEndOf
    0.78
     useRouter
    0.75
     itſelf
    0.72
    ^(@)
    0.71
     myſelf
    0.69
    TableBody
    0.69
     Jefus
    0.66
     AssemblyTitle
    0.66
     TextInputType
    0.64
    Activations Density 3.726%

    No Known Activations