© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14198
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · 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
     propOrder
    -0.66
    stdc
    -0.64
     megh
    -0.57
     дописавши
    -0.57
     saites
    -0.56
     Parigi
    -0.54
     разом
    -0.52
    ValueGenerated
    -0.51
     sociais
    -0.51
    protoimpl
    -0.51
    POSITIVE LOGITS
     CanadaChoose
    0.76
    Searcher
    0.64
    ēju
    0.57
     cac
    0.55
    APOLIS
    0.54
    chooser
    0.54
    ритори
    0.54
    voit
    0.53
    brainly
    0.52
     Fama
    0.52
    Activations Density 4.690%

    No Known Activations