© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1540
    Prev
    Next
    INDEX
    Explanations

    clauses with the word "and"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     trajets
    -0.59
    protoimpl
    -0.47
    toso
    -0.44
     Clean
    -0.43
     Rim
    -0.43
    Clean
    -0.42
    Jereo
    -0.42
    SourceChecksum
    -0.41
     useCallback
    -0.41
     charter
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.81
    发表于
    0.69
     Monfieur
    0.64
     محفوظة
    0.62
     pleaſure
    0.60
    MemoryWarning
    0.60
    CloseOperation
    0.59
    dafx
    0.59
    WarningLevel
    0.59
    enderror
    0.58
    Activations Density 0.614%

    No Known Activations