© 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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14681
    Prev
    Next
    INDEX
    Explanations

    abstract nouns ending in -ness, -tion, -ity, or -ship, as well as words generally associated with the topics of religion, health, and organization

    oai_token-act-pair · gemini-2.0-flash

    Qualities/attributes

    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
     smoothness
    -0.82
     resilience
    -0.77
     generosity
    -0.77
     professionalism
    -0.77
     creativity
    -0.77
    <bos>
    -0.77
     correctness
    -0.76
     independence
    -0.75
     stability
    -0.75
     effectiveness
    -0.74
    POSITIVE LOGITS
    setVerticalGroup
    0.51
    AnimationsModule
    0.47
    sphase
    0.47
    尽
    0.46
    camisa
    0.46
     tục
    0.45
    kson
    0.45
    pantalon
    0.45
    płat
    0.45
     đạt
    0.44
    Activations Density 12.312%

    No Known Activations