© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9993
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to biology, microbiology, immunology, or genetics, especially in informal language

    oai_token-act-pair · gemini-2.0-flash

    Code paths and gut biology

    np_max-act · gemini-2.0-flash
    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
     виправивши
    -0.95
    MENAFN
    -0.92
    ChildScrollView
    -0.90
     iſt
    -0.85
    tvguidetime
    -0.84
    adaptiveStyles
    -0.81
     Efq
    -0.81
     للمعارف
    -0.81
     myſelf
    -0.79
    RegressionTest
    -0.79
    POSITIVE LOGITS
     the
    0.54
     assays
    0.49
     capacitors
    0.48
     biologique
    0.47
     annuelle
    0.45
     ristoranti
    0.45
    <em>
    0.44
     Lass
    0.44
     mitosis
    0.44
     Cohn
    0.44
    Activations Density 6.924%

    No Known Activations