© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10997
    Prev
    Next
    INDEX
    Explanations

    mentions of Christian saints, especially Saint Patrick, and place names, especially Santa Fe in the US state of New Mexico

    oai_token-act-pair · gemini-2.0-flash

    patrick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -0.83
    ViewChild
    -0.66
     Exactos
    -0.66
     تانيه
    -0.64
    RenderAtEndOf
    -0.63
     kasarigan
    -0.61
     textStatus
    -0.60
    AndroidJUnit
    -0.60
    AnchorStyles
    -0.60
     WebDriverWait
    -0.58
    POSITIVE LOGITS
     ioutil
    0.59
    )))
    0.58
    כן
    0.54
    masing
    0.52
    )));
    0.52
    лтемелер
    0.52
    }")
    0.51
     şun
    0.50
    idot
    0.50
     fotball
    0.50
    Activations Density 1.045%

    No Known Activations