© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8313
    Prev
    Next
    INDEX
    Explanations

    table dividers in research papers

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    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
     CreateTagHelper
    -0.93
     myſelf
    -0.82
     Monfieur
    -0.82
     Efq
    -0.81
     pinulongan
    -0.81
     Majefty
    -0.80
     Jefus
    -0.79
    تقاوى
    -0.77
     الحره
    -0.77
     himſelf
    -0.75
    POSITIVE LOGITS
    */),
    0.54
    》。
    0.48
    фона
    0.45
    idenav
    0.44
    İstinadlar
    0.44
    :✨
    0.43
    чью
    0.42
     Wiktionnaire
    0.42
    '.
    0.41
     supaya
    0.41
    Activations Density 4.090%

    No Known Activations