© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7439
    Prev
    Next
    INDEX
    Explanations

    Arabic names and related tribal terms from the early Islamic period.

    oai_token-act-pair · gemini-2.0-flash

    Arabic context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WORTH
    -0.40
    worth
    -0.40
    ונות
    -0.38
    Dang
    -0.37
    mixed
    -0.37
    混
    -0.36
    ted
    -0.36
    rib
    -0.35
     armed
    -0.35
    西部
    -0.35
    POSITIVE LOGITS
    queryInterface
    0.85
     للمعارف
    0.77
    FunctionFlags
    0.75
     Italijani
    0.74
     مشين
    0.74
    NameInMap
    0.73
    Personensuche
    0.69
    ⓧ
    0.69
    BeginContext
    0.69
     lenker
    0.66
    Activations Density 0.284%

    No Known Activations