© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1523
    Prev
    Next
    INDEX
    Explanations

    capitalized terms, especially acronyms and names, from a variety of contexts (fantasy, music, medicine)

    oai_token-act-pair · gemini-2.0-flash

    Character/artist names

    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
    UserScript
    -0.61
    ScopeManager
    -0.54
    jstor
    -0.50
    Erreferentziak
    -0.48
    WindowConstants
    -0.44
     comunit
    -0.44
    cstdio
    -0.43
    Билгалдахарш
    -0.43
    anna
    -0.42
     touch
    -0.42
    POSITIVE LOGITS
    Демографія
    0.66
     &___
    0.64
    DoubleQuotes
    0.64
     ThemeData
    0.61
     ſta
    0.58
    ="@+
    0.57
     ſhall
    0.54
     deſt
    0.53
     ſon
    0.53
    disfraz
    0.52
    Activations Density 0.630%

    No Known Activations