© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4122
    Prev
    Next
    INDEX
    Explanations

    instances of the word "emphasis" followed by "added."

    oai_token-act-pair · gemini-2.0-flash

    emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     الاطلاع
    -0.55
     inform
    -0.54
    ừng
    -0.53
     muhimu
    -0.48
     الدولى
    -0.47
     information
    -0.47
    tencent
    -0.46
    Inform
    -0.46
    érieure
    -0.45
     pries
    -0.45
    POSITIVE LOGITS
    CodedInputStream
    0.81
    الحياه
    0.73
    MergeFrom
    0.69
    RenderAtEndOf
    0.68
    queryInterface
    0.62
     חיצוניים
    0.60
    轭
    0.57
    pubmed
    0.57
    RTLD
    0.57
    ApiModelProperty
    0.56
    Activations Density 3.199%

    No Known Activations