© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    angle brackets, URLs and other markup especially from XML-like data

    oai_token-act-pair · gemini-2.0-flash

    XML-like markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Bande
    -0.46
    Werdegang
    -0.44
     auras
    -0.44
     JComboBox
    -0.42
    hush
    -0.42
     Motorsports
    -0.42
    MessageInfo
    -0.41
    usy
    -0.41
     SqlParameter
    -0.41
    #__
    -0.41
    POSITIVE LOGITS
    dafx
    0.74
     Normdatei
    0.74
     Administrativna
    0.69
    ngdoc
    0.67
    Capítulo
    0.67
     <<<<<<<<<<<<<<
    0.66
    хьтан
    0.65
    脚注の使い方
    0.65
    Personendaten
    0.63
    Geplaatst
    0.62
    Activations Density 9.266%

    No Known Activations