© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14927
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    RegressionTest
    -0.70
    delwed
    -0.58
     дописавши
    -0.57
    htë
    -0.57
    webElementXpaths
    -0.56
    脚注の使い方
    -0.55
     autorytatywna
    -0.53
     jScrollPane
    -0.53
     الرياضيه
    -0.52
    Datuak
    -0.52
    POSITIVE LOGITS
    board
    0.45
     COUN
    0.43
    PropertyValue
    0.42
     lo
    0.40
    !(:
    0.39
     mis
    0.39
    BOARD
    0.39
    ếp
    0.39
     lccn
    0.39
     dess
    0.39
    Activations Density 4.025%

    No Known Activations