© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7178
    Prev
    Next
    INDEX
    Explanations

    words indicating someone's origin, legal standing, or profession

    oai_token-act-pair · gemini-2.0-flash

    native or supreme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    çuk
    -0.45
     Kem
    -0.45
    AlterField
    -0.41
    痛
    -0.41
    Kem
    -0.40
    欢
    -0.39
    Predecesor
    -0.39
    piel
    -0.38
    ish
    -0.37
     Staging
    -0.36
    POSITIVE LOGITS
     AssemblyTitle
    0.88
     للمعارف
    0.84
    IsMutable
    0.79
    ."</
    0.77
     }}"></
    0.77
    MessageTagHelper
    0.76
     intptr
    0.76
    AsUp
    0.75
     nahilalakip
    0.75
    ⓧ
    0.73
    Activations Density 0.455%

    No Known Activations