© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6699
    Prev
    Next
    INDEX
    Explanations

    words or code related to computing, electronics, and scientific or medical documents

    oai_token-act-pair · gemini-2.0-flash

    code and research text

    np_max-act · gemini-2.0-flash

    rare words Method used: 3 — detected uncommon/technical/foreign words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    brainly
    -0.86
     يتيمه
    -0.83
    AddTagHelper
    -0.83
     שוליים
    -0.82
    клопе
    -0.74
    +#+#
    -0.73
    idamente
    -0.73
     وتسجيلات
    -0.72
    SEGUIR
    -0.71
     cherchés
    -0.70
    POSITIVE LOGITS
    signable
    0.53
    umman
    0.52
    ObjectContext
    0.51
     Mühle
    0.51
     damska
    0.50
    ograma
    0.48
    ↵↵
    0.48
     highly
    0.48
    RegressionTest
    0.48
    vaadin
    0.47
    Activations Density 13.179%

    No Known Activations