© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15340
    Prev
    Next
    INDEX
    Explanations

    file paths, references, code elements, and company and family nomenclature

    oai_token-act-pair · gemini-2.0-flash

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     EconPapers
    -0.88
     تانيه
    -0.55
    kháu
    -0.54
     erbjud
    -0.53
    uolo
    -0.52
     referenties
    -0.52
    zyden
    -0.51
    Fordítás
    -0.50
    !*\
    -0.50
    antaranya
    -0.49
    POSITIVE LOGITS
     utafitiHapana
    0.72
    oredCriteria
    0.71
    CppMethod
    0.64
    rawDesc
    0.62
     Drapeau
    0.59
     Bic
    0.57
    Hochspringen
    0.56
    ьаж
    0.56
    memoized
    0.55
    ItemBackground
    0.54
    Activations Density 20.971%

    No Known Activations