© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14080
    Prev
    Next
    INDEX
    Explanations

    instances of scientific terminology and related vocabulary across various fields

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    évaluateur
    -0.57
    +#+
    -0.57
    SourceChecksum
    -0.57
    Kanpo
    -0.54
    Билгалдахарш
    -0.50
    UnsafeEnabled
    -0.50
     ویکی‌پدیای
    -0.50
    TagMode
    -0.49
    bech
    -0.49
     مختلف
    -0.48
    POSITIVE LOGITS
     sommeil
    0.56
     Subject
    0.54
    Carriera
    0.52
     subjects
    0.51
     yoksa
    0.50
     unreleased
    0.49
    Subject
    0.48
    assage
    0.48
     undi
    0.48
    URLException
    0.47
    Activations Density 18.410%

    No Known Activations