© 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. 8389
    Prev
    Next
    INDEX
    Explanations

    Chinese text having to do with dictionaries and character encodings

    oai_token-act-pair · gemini-2.0-flash

    code snippets with mixed languages

    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
    ValueStyle
    -0.69
     EconPapers
    -0.62
     للمعارف
    -0.62
    Geplaatst
    -0.61
     est
    -0.60
    :✨
    -0.57
    parsedMessage
    -0.56
    KommentareTeilen
    -0.54
     peroxidase
    -0.54
     onCreateView
    -0.53
    POSITIVE LOGITS
    abit
    0.57
    ệu
    0.54
    /**
    0.53
     dones
    0.52
     <=",
    0.52
    jsonwebtoken
    0.51
    bjs
    0.50
     становника
    0.50
     ziren
    0.48
     gainera
    0.47
    Activations Density 0.397%

    No Known Activations