© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13529
    Prev
    Next
    INDEX
    Explanations

    snippets of PHP or Javascript code

    oai_token-act-pair · gemini-2.0-flash

    portuguese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    MessageTagHelper
    -0.65
     onBackPressed
    -0.63
    #
    -0.63
     en
    -0.60
     into
    -0.59
     centre
    -0.58
     via
    -0.54
     vi
    -0.52
     Bro
    -0.52
     Qu
    -0.51
    POSITIVE LOGITS
     rempliss
    0.79
     habet
    0.77
     pouvoit
    0.77
     Anſ
    0.76
     vectorielles
    0.73
     titolata
    0.73
     mauva
    0.73
     plufieurs
    0.72
     optique
    0.72
     feroit
    0.70
    Activations Density 0.158%

    No Known Activations