© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3674
    Prev
    Next
    INDEX
    Explanations

    the word "heavy" and words associated with it like metals and alcohol

    oai_token-act-pair · gemini-2.0-flash

    references to "heavy"

    np_token-act-pair-logits · gpt-4o-mini

    heavy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ***!
    -0.77
    CompilerServices
    -0.75
     createState
    -0.73
    NameInMap
    -0.73
    RegressionTest
    -0.68
     Мексичка
    -0.66
    Personendaten
    -0.66
    setVerticalGroup
    -0.66
     ComVisible
    -0.65
    MockBean
    -0.64
    POSITIVE LOGITS
    PAIGN
    0.62
     duty
    0.61
     DUTY
    0.56
     Duty
    0.54
    Duty
    0.52
     car
    0.51
     carga
    0.50
     metal
    0.50
    poids
    0.48
    chinen
    0.47
    Activations Density 1.150%

    No Known Activations