© 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. 16328
    Prev
    Next
    INDEX
    Explanations

    sentences that ask or consider "what does it mean."

    oai_token-act-pair · gemini-2.0-flash

    mean

    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
    Negative Logits
     defaultstate
    -0.86
    AsUp
    -0.83
    PreferredItem
    -0.79
    lgari
    -0.68
    principalTable
    -0.66
    AnchorTagHelper
    -0.65
    ValueStyle
    -0.61
    المشاركات
    -0.61
     تضيفلها
    -0.61
    AndroidJUnit
    -0.61
    POSITIVE LOGITS
     intim
    0.42
    mény
    0.39
     Sanford
    0.39
     iParam
    0.39
    مراجع
    0.38
    frig
    0.38
     físico
    0.38
    …~
    0.38
    zellan
    0.38
     Titi
    0.37
    Activations Density 3.380%

    No Known Activations