© 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. 11166
    Prev
    Next
    INDEX
    Explanations

    words and symbols common in scientific and technical documents, especially related to measurements, numbers, and parameters.

    oai_token-act-pair · gemini-2.0-flash

    math/science formulas

    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
     passés
    -0.71
     oreilles
    -0.70
     devenus
    -0.68
     détru
    -0.68
     européennes
    -0.68
     élevés
    -0.67
     $\
    -0.67
     étend
    -0.66
     démocr
    -0.66
     blessés
    -0.65
    POSITIVE LOGITS
    aarrggbb
    0.74
     gynhyrchwyd
    0.68
    yntaxException
    0.65
     ddelweddau
    0.59
     }}$}
    0.58
    乓
    0.58
     XNUMX
    0.56
    SceneManagement
    0.56
    kháu
    0.56
     itſelf
    0.56
    Activations Density 7.890%

    No Known Activations