© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8624
    Prev
    Next
    INDEX
    Explanations

    language related to legal documents, specifically dealing with employment taxes.

    oai_token-act-pair · gemini-2.0-flash

    social

    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
    发表于
    -0.61
     跳转至
    -0.54
    ImageContext
    -0.54
     Numerology
    -0.52
    ObjectContext
    -0.49
    regon
    -0.45
    ographia
    -0.44
    alore
    -0.43
    avaj
    -0.43
    
    -0.43
    POSITIVE LOGITS
     social
    2.70
     Social
    2.61
    Social
    2.58
    social
    2.45
     SOCIAL
    2.38
    SOCIAL
    2.23
     sociale
    1.92
     sosial
    1.90
     sociales
    1.85
     sociaux
    1.83
    Activations Density 5.578%

    No Known Activations