© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with numbers and abbreviations for scientific terms

    oai_token-act-pair · gemini-2.0-flash

    Parentheses and commas

    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
    ViewFeatures
    -0.54
     Krim
    -0.47
    ViewImports
    -0.47
     اكتوبر
    -0.43
    ExtendWith
    -0.42
     stället
    -0.41
    WindowConstants
    -0.41
     []:
    -0.41
     JpaRepository
    -0.40
    :✨
    -0.40
    POSITIVE LOGITS
    <bos>
    0.80
     Normdatei
    0.67
    posedge
    0.53
    optic
    0.48
    Novo
    0.47
    tahui
    0.47
    sees
    0.46
     становника
    0.45
    σία
    0.45
    ophobia
    0.45
    Activations Density 2.450%

    No Known Activations