© 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. 977
    Prev
    Next
    INDEX
    Explanations

    a wide variety of mostly technical terms, especially from scientific and legal domains

    oai_token-act-pair · gemini-2.0-flash

    technical/academic language

    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
     חיצוניים
    -0.71
     AspNetCore
    -0.67
    Étymologie
    -0.57
    ratulations
    -0.56
    herz
    -0.54
    optarg
    -0.54
    ธอ
    -0.54
    sitions
    -0.54
    تقاوى
    -0.54
     battre
    -0.53
    POSITIVE LOGITS
     الدولى
    0.56
     <<<<<<<<<<<<<<
    0.54
    zarchiwizowane
    0.53
     مواليد
    0.48
    RegressionTest
    0.48
    ByteBuf
    0.47
    SizeF
    0.46
     коды
    0.45
    парта
    0.44
     INTERESAR
    0.44
    Activations Density 0.281%

    No Known Activations