© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4567
    Prev
    Next
    INDEX
    Explanations

    the word "South" and anything related to it, including countries and regions

    oai_token-act-pair · gemini-2.0-flash

    south

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    CppCodeGen
    -0.52
     désolés
    -0.47
    TypeDef
    -0.47
    MethodManager
    -0.46
    IActionResult
    -0.45
    andReturn
    -0.44
    ządu
    -0.44
    odin
    -0.44
    mycin
    -0.43
    rungen
    -0.43
    POSITIVE LOGITS
     propOrder
    0.72
    :✨
    0.62
     oprot
    0.61
     Paglinawan
    0.60
    esgue
    0.59
     mergeFrom
    0.59
     entanto
    0.58
    XmlAccessorType
    0.58
    ervare
    0.58
    ikistan
    0.57
    Activations Density 1.318%

    No Known Activations