© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11461
    Prev
    Next
    INDEX
    Explanations

    terms related to the immune system, cancer, and scientific studies using animal models

    oai_token-act-pair · gemini-2.0-flash

    T cell antigen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     يتيمه
    -0.76
     AssemblyCulture
    -0.75
     disambiguazione
    -0.71
    PhysRevD
    -0.71
    Datuak
    -0.68
    PYX
    -0.68
    Pranala
    -0.68
    HtmlAttribute
    -0.68
     chi̍t
    -0.66
    Personendaten
    -0.64
    POSITIVE LOGITS
     sfor
    0.48
    put
    0.46
     theirs
    0.44
     them
    0.43
     himo
    0.43
    환
    0.43
     everlasting
    0.42
     Korean
    0.42
    nění
    0.42
     yesterday
    0.41
    Activations Density 1.370%

    No Known Activations