© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12753
    Prev
    Next
    INDEX
    Explanations

    the word "rise" and sometimes "decay"

    oai_token-act-pair · gemini-2.0-flash

    rise

    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
     rise
    -2.69
     Rise
    -2.16
    Rise
    -2.11
    rise
    -2.06
     rises
    -1.97
     rising
    -1.92
    Rising
    -1.63
    rising
    -1.61
     RISE
    -1.60
     Rising
    -1.59
    POSITIVE LOGITS
     שוליים
    1.11
     InputDecoration
    1.11
    ########.
    1.07
     myſelf
    1.05
     itſelf
    1.05
     للاسماء
    1.03
    InputBorder
    1.01
    awtextra
    0.98
     StatefulWidget
    0.97
    IntoConstraints
    0.94
    Activations Density 1.122%

    No Known Activations