© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4068
    Prev
    Next
    INDEX
    Explanations

    people's names, especially French names

    oai_token-act-pair · gemini-2.0-flash

    Lists of names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    addCriterion
    -0.79
    BeginContext
    -0.71
    WriteAttribute
    -0.69
    ArrowToggle
    -0.66
     continúas
    -0.63
    脚注の使い方
    -0.61
     Exacts
    -0.60
    RectangleBorder
    -0.60
    awaiter
    -0.60
    Personendaten
    -0.59
    POSITIVE LOGITS
    Syl
    0.58
     Pascal
    0.56
     Cyril
    0.56
     Florence
    0.54
     Vincent
    0.51
     Quentin
    0.50
     Yn
    0.49
     Florent
    0.48
    UDA
    0.47
    hood
    0.47
    Activations Density 1.872%

    No Known Activations