© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12466
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to institutions, grants, awards, and funding in scientific research

    oai_token-act-pair · gemini-2.0-flash

    words related to investigators and research

    np_token-act-pair-logits · gpt-4o-mini

    investigator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GroupLayout
    -0.64
     propOrder
    -0.60
    Personendaten
    -0.57
    ंदीखरीदारी
    -0.57
    ContentAsync
    -0.57
    Controllo
    -0.54
     يتيمه
    -0.54
    Notae
    -0.52
     sellers
    -0.52
    Bibliographie
    -0.52
    POSITIVE LOGITS
     investigators
    0.95
    Principal
    0.87
    Investigators
    0.85
    investig
    0.84
     investigator
    0.83
     Principal
    0.82
     principal
    0.80
    principal
    0.79
     Investigators
    0.79
    Investig
    0.75
    Activations Density 4.065%

    No Known Activations