Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 954
    Prev
    Next
    INDEX
    Explanations

    words related to quantities and declines, especially in financial or statistical contexts

    oai_token-act-pair · gemini-2.0-flash

    Increase or decrease

    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
    Климат
    -0.54
    duğu
    -0.52
     følge
    -0.50
    }*/
    -0.49
    excellents
    -0.49
     Audiodateien
    -0.48
     supplémentaires
    -0.48
     olmaz
    -0.48
    ɬ
    -0.46
    存于互联网档案馆
    -0.46
    POSITIVE LOGITS
    InjectAttribute
    0.64
    WriteAttribute
    0.62
     CreateTagHelper
    0.54
    addCriterion
    0.52
    AnimationsModule
    0.52
    enumi
    0.51
     onResponse
    0.50
    ristmas
    0.49
    writeField
    0.49
     Seeder
    0.49
    Activations Density 14.051%

    No Known Activations