© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15509
    Prev
    Next
    INDEX
    Explanations

    prepositions and other short grammar words, particularly "by", "to", "from", "of", phrases using "more", and passages talking about time, especially "after".

    oai_token-act-pair · gemini-2.0-flash

    after

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     onely
    -0.57
     BorderRadius
    -0.55
    исленность
    -0.53
    netbeans
    -0.53
     bandana
    -0.52
    phytes
    -0.51
     gogh
    -0.50
     Raceway
    -0.50
     FishBase
    -0.50
    Analytic
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.69
     مشين
    0.60
    \{\\
    0.59
    ProcessEvent
    0.53
     OFDb
    0.52
     ویکی‌پدیای
    0.51
    StoryboardSegue
    0.50
     ✭✭
    0.49
    TagMode
    0.49
    ItemLayout
    0.48
    Activations Density 11.418%

    No Known Activations