© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15181
    Prev
    Next
    INDEX
    Explanations

    the word "childhood," sometimes in combination with related words like "infancy", "force", "renovation", or "part"

    oai_token-act-pair · gemini-2.0-flash

    childhood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    BeginContext
    -0.59
    o
    -0.56
    y
    -0.53
     alliances
    -0.53
     Torn
    -0.50
     subsidized
    -0.49
    eaus
    -0.49
    openConnection
    -0.48
    DeleteMapping
    -0.47
    edes
    -0.46
    POSITIVE LOGITS
     auffi
    0.97
    amaño
    0.91
    Rüyada
    0.83
     Monfieur
    0.82
    :✨
    0.79
     málaga
    0.79
     Jurí
    0.78
     Conſ
    0.78
     Infór
    0.77
     Diſ
    0.75
    Activations Density 1.798%

    No Known Activations