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. 725
    Prev
    Next
    INDEX
    Explanations

    vocabulary terms that could be found in academic or medical research papers.

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    StoryboardSegue
    -0.83
    IsMutable
    -0.79
    تقاوى
    -0.77
    DockStyle
    -0.76
     незавершена
    -0.75
     للمعارف
    -0.75
    ReusableCell
    -0.75
     tartalomajánló
    -0.73
    TProtocol
    -0.72
    oredCriteria
    -0.72
    POSITIVE LOGITS
    Vay
    0.43
    DNA
    0.43
    יל
    0.42
    ganza
    0.41
     required
    0.41
     already
    0.41
    ReadOnly
    0.40
    富
    0.40
    kez
    0.40
    return
    0.40
    Activations Density 60.826%

    No Known Activations