© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6115
    Prev
    Next
    INDEX
    Explanations

    words related to stool sample collection and testing, as well as mentions of viruses and health officials

    oai_token-act-pair · gemini-2.0-flash

    Medical tests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Tests
    -1.26
     Test
    -1.25
     TEST
    -1.20
     Testing
    -1.20
     tests
    -1.20
     test
    -1.20
    Test
    -1.17
     TESTS
    -1.16
     testing
    -1.16
    Testing
    -1.11
    POSITIVE LOGITS
     ujednoznacz
    0.69
     disambiguazione
    0.68
     ExecuteAsync
    0.65
    bewerken
    0.61
     BoxFit
    0.61
     مشين
    0.59
    IsContent
    0.58
    HtmlAttribute
    0.57
     Réponses
    0.57
    KommentareTeilen
    0.54
    Activations Density 2.734%

    No Known Activations