© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14526
    Prev
    Next
    INDEX
    Explanations

    the word 'best', but also recognizes when it is used ironically as 'worst', and picks up related words like 'winner'.

    oai_token-act-pair · gemini-2.0-flash

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     best
    -2.36
    Best
    -2.11
    best
    -2.06
     Best
    -1.95
     BEST
    -1.66
    BEST
    -1.56
     mejores
    -1.38
     meilleures
    -1.30
    最佳
    -1.26
     melhores
    -1.25
    POSITIVE LOGITS
    jgl
    0.67
    rencies
    0.64
    setContentView
    0.63
     endforeach
    0.62
    glEnd
    0.60
    roek
    0.59
     StatefulWidget
    0.59
     consultato
    0.57
    AnchorTagHelper
    0.57
    hyrchwyd
    0.57
    Activations Density 2.577%

    No Known Activations