© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 293
    Prev
    Next
    INDEX
    Explanations

    legal jargon and citations, especially referencing court decisions and statutes

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     المعيارى
    -0.77
    expandindo
    -0.73
    GEBURTSDATUM
    -0.65
    ViewFeatures
    -0.64
     beginnetje
    -0.61
     مشين
    -0.57
     Wikimedijinoj
    -0.57
    rrggbb
    -0.57
    出版年
    -0.56
     насељу
    -0.56
    POSITIVE LOGITS
    ViewImports
    0.55
    Ranks
    0.50
    ensible
    0.49
    BufferException
    0.48
     crédit
    0.48
    beiros
    0.48
    vertebrate
    0.47
    enseur
    0.46
     tamper
    0.45
    டம்
    0.45
    Activations Density 7.473%

    No Known Activations