© 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. 4499
    Prev
    Next
    INDEX
    Explanations

    capitalized letters representing genes and proteins in publications

    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_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
     mijne
    -0.95
    <bos>
    -0.93
     дописавши
    -0.86
     titolata
    -0.79
    ########.
    -0.77
    IntoConstraints
    -0.73
    Personensuche
    -0.72
     ***!
    -0.72
    InjectAttribute
    -0.70
    Tikang
    -0.70
    POSITIVE LOGITS
    benar
    0.60
     co
    0.59
     Ber
    0.55
    Portale
    0.54
     full
    0.54
    inthe
    0.52
     sign
    0.51
     Kass
    0.51
     bound
    0.51
     sur
    0.50
    Activations Density 4.693%

    No Known Activations