© 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. 1321
    Prev
    Next
    INDEX
    Explanations

    words from scientific studies, especially related to abnormalities and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    Large degree adverbs

    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
     وتسجيلات
    -0.79
    MigrationBuilder
    -0.74
    tvguidetime
    -0.74
     heterogeneous
    -0.64
    rungsseite
    -0.63
     disambiguazione
    -0.63
     initComponents
    -0.63
     uniformity
    -0.61
    脚注の使い方
    -0.61
    PreferredItem
    -0.60
    POSITIVE LOGITS
    principalTable
    0.60
    TabStop
    0.47
     أث
    0.43
    resso
    0.41
    UAGES
    0.40
     podjela
    0.40
    stops
    0.39
    untas
    0.39
     backstage
    0.39
    ścić
    0.38
    Activations Density 57.911%

    No Known Activations