© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10837
    Prev
    Next
    INDEX
    Explanations

    text about children going to school.

    oai_token-act-pair · gemini-2.0-flash

    parenting and children

    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
    примеча
    -0.45
    AntiForgeryToken
    -0.44
     Wea
    -0.37
    żs
    -0.37
     cit
    -0.37
    lacian
    -0.36
    πουργ
    -0.36
    痩
    -0.35
     Weights
    -0.35
     lä
    -0.35
    POSITIVE LOGITS
    RectangleBorder
    0.81
     pinulongan
    0.74
     siblings
    0.74
     ModelExpression
    0.74
     moms
    0.74
     grandparents
    0.72
    siblings
    0.72
    }{*}{}
    0.72
     parents
    0.71
     Geschw
    0.71
    Activations Density 30.998%

    No Known Activations