© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7692
    Prev
    Next
    INDEX
    Explanations

    text from research papers on the subject of cells, and regulatory factors

    oai_token-act-pair · gemini-2.0-flash

    terms and concepts related to T cell signaling and differentiation

    np_token-act-pair-logits · gpt-4o-mini

    T cells and immunity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    protoimpl
    -0.67
     BoxDecoration
    -0.66
     morire
    -0.65
     հղումներ
    -0.65
     fidé
    -0.65
     Beſ
    -0.65
    قایناق‌لار
    -0.63
     surla
    -0.61
    réhen
    -0.61
     Theſe
    -0.58
    POSITIVE LOGITS
     T
    0.52
    Personensuche
    0.50
    dAtA
    0.47
     mon
    0.45
     I
    0.44
    RegressionTest
    0.42
    InlineData
    0.42
    ウンジ
    0.42
     monoc
    0.42
     Mon
    0.41
    Activations Density 3.292%

    No Known Activations