© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5113
    Prev
    Next
    INDEX
    Explanations

    articles discussing health and nutrition by country

    oai_token-act-pair · gemini-2.0-flash

    technical coding terms or components

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

    The

    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
    More
    -0.58
    more
    -0.52
     more
    -0.50
    chengladbach
    -0.49
    Values
    -0.45
    ValueStyle
    -0.45
    WriteTagHelper
    -0.44
     More
    -0.43
     OnInit
    -0.39
     lebih
    -0.38
    POSITIVE LOGITS
     resourceCulture
    0.93
     ComVisible
    0.85
     propOrder
    0.81
    expandindo
    0.80
     صوتيه
    0.79
     JAXBElement
    0.76
     Baillargeon
    0.75
    IsContent
    0.75
     "..\..\..\
    0.73
    SourceChecksum
    0.72
    Activations Density 1.810%

    No Known Activations