© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    the word "good" followed by a noun or adjective

    oai_token-act-pair · gemini-2.0-flash

    good

    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
     feroit
    -0.66
    ChildScrollView
    -0.66
    TintMode
    -0.65
     vermelhas
    -0.65
     imprimée
    -0.65
    tvguidetime
    -0.62
    Зноскі
    -0.62
    Tembelea
    -0.60
     MainAxisSize
    -0.59
    EndGlobalSection
    -0.59
    POSITIVE LOGITS
     deal
    0.59
     opportunity
    0.50
    மே
    0.49
    andaag
    0.47
    hearted
    0.47
     alternative
    0.47
    abras
    0.47
    iende
    0.46
    WriteAttribute
    0.46
    irited
    0.45
    Activations Density 1.703%

    No Known Activations