© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    words related to medical research and treatment

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "different"

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

    different

    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
    mtrl
    -0.78
    XmlAccessType
    -0.77
     unknownFields
    -0.73
    IUrlHelper
    -0.68
    UserScript
    -0.68
    setVerticalGroup
    -0.68
    RegressionTest
    -0.66
    __":
    -0.64
    Становништво
    -0.63
    AndroidJUnit
    -0.63
    POSITIVE LOGITS
     different
    3.16
    different
    2.88
     Different
    2.72
    Different
    2.69
     diferentes
    2.22
     DIFFERENT
    2.22
    不同
    1.98
    不同的
    1.94
     diferente
    1.88
     différentes
    1.87
    Activations Density 6.040%

    No Known Activations