© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11435
    Prev
    Next
    INDEX
    Explanations

    the word "and" and words that often surround it

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     protoimpl
    -0.85
     تضيفلها
    -0.77
    SceneManagement
    -0.76
     pinulongan
    -0.68
    WriteBarrier
    -0.68
     SafeMath
    -0.66
    LabelTagHelper
    -0.66
     cherchés
    -0.65
    homonymie
    -0.65
    queryInterface
    -0.64
    POSITIVE LOGITS
    Surprisingly
    0.46
     AssemblyProduct
    0.45
     Surprisingly
    0.44
     surprisingly
    0.43
    ARIO
    0.43
    izeit
    0.39
    rowser
    0.39
     found
    0.39
    cza
    0.39
    プロン
    0.38
    Activations Density 0.260%

    No Known Activations