© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11592
    Prev
    Next
    INDEX
    Explanations

    certain occurrences of the words "den" and "dem" and the place name "Hong Kong" and the place name "Los Angeles"

    oai_token-act-pair · gemini-2.0-flash

    Cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     dem
    -0.81
     den
    -0.68
    .
    -0.52
    dem
    -0.52
     
    -0.50
    ).
    -0.49
    ignon
    -0.46
     de
    -0.46
     vi
    -0.45
    DEM
    -0.45
    POSITIVE LOGITS
     للمعارف
    1.09
    存于互联网档案馆
    0.99
     referenties
    0.93
    MessageTagHelper
    0.92
     يتيمه
    0.90
    IntoConstraints
    0.90
     المعيارى
    0.89
     ExecuteAsync
    0.89
    GOTREF
    0.87
     myſelf
    0.87
    Activations Density 0.353%

    No Known Activations