© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8858
    Prev
    Next
    INDEX
    Explanations

    words and phrases that would appear in scientific or academic papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    AndEndTag
    -0.70
    новниш
    -0.65
    
    -0.65
    исленность
    -0.65
    béco
    -0.65
     Chwiliwch
    -0.65
     Вікі
    -0.64
    InjectAttribute
    -0.64
     Efq
    -0.64
    niająca
    -0.63
    POSITIVE LOGITS
    <eos>
    0.53
     another
    0.45
     Stern
    0.45
    ねて
    0.41
     Greet
    0.41
     Se
    0.40
     Low
    0.40
    
    0.40
     vis
    0.39
    طيع
    0.39
    Activations Density 5.298%

    No Known Activations