Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 714
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, especially those involving the defendant being aware of their rights

    oai_token-act-pair · gemini-2.0-flash

    legal rights

    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
     насељу
    -0.78
    RegressionTest
    -0.73
     المعيارى
    -0.72
     صوتيه
    -0.71
     Offisielt
    -0.69
    
    -0.67
    rostis
    -0.66
     الحره
    -0.66
    rhosis
    -0.65
    rentices
    -0.65
    POSITIVE LOGITS
    ActivityCompat
    0.49
    英语
    0.46
    èdia
    0.44
    autoconfigure
    0.42
    angu
    0.41
    nloa
    0.40
    VIA
    0.40
     st
    0.39
    варь
    0.39
     full
    0.37
    Activations Density 1.173%

    No Known Activations