© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11680
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations within scientific papers

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TypedDataSet
    -0.89
    AddTagHelper
    -0.73
     oprot
    -0.67
     resourceCulture
    -0.63
     Paglinawan
    -0.62
    SequentialGroup
    -0.61
    IsMutable
    -0.60
    contentLoaded
    -0.60
    +#+#
    -0.60
    webElementXpaths
    -0.59
    POSITIVE LOGITS
    mybatisplus
    0.54
    بوابة
    0.51
    مراجع
    0.50
    Referencies
    0.50
     Wikimédia
    0.49
    ✭✭
    0.47
    marry
    0.44
     belang
    0.42
     '\\;'
    0.41
     تانيه
    0.40
    Activations Density 1.893%

    No Known Activations