© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11477
    Prev
    Next
    INDEX
    Explanations

    passages about business purchases emphasizing that company money is spent, not one's own

    oai_token-act-pair · gemini-2.0-flash

    marketing/documentation text

    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
    準
    -0.43
    /*
    -0.40
     zám
    -0.39
    formik
    -0.38
     komple
    -0.38
     Commission
    -0.38
    руя
    -0.38
    غان
    -0.36
     kom
    -0.36
    batore
    -0.36
    POSITIVE LOGITS
    Geplaatst
    0.77
     useAppContext
    0.73
    oa̍t
    0.72
     Numerade
    0.70
    kháu
    0.69
    ModelAdmin
    0.69
     سكانية
    0.69
     XCTest
    0.65
    TestingModule
    0.65
     Thro
    0.65
    Activations Density 0.962%

    No Known Activations