© 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. 2053
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical research and reporting, especially clinical trials

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with specific capital letters

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

    Medical contexts

    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
     Houſe
    -0.96
    ſelves
    -0.87
     Efq
    -0.86
    ſelf
    -0.84
     Theſe
    -0.82
     Reſ
    -0.81
    Autoritní
    -0.81
     Monfieur
    -0.80
     Diſ
    -0.78
     Jefus
    -0.75
    POSITIVE LOGITS
     W
    0.88
     R
    0.83
     M
    0.83
     T
    0.80
     H
    0.80
     C
    0.78
     L
    0.78
     CM
    0.77
     AS
    0.77
     G
    0.76
    Activations Density 41.167%

    No Known Activations