© 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. 5112
    Prev
    Next
    INDEX
    Explanations

    personal stories about children

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "give"

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

    Caring and comforting actions

    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
     AssemblyCulture
    -0.84
    TagHelper
    -0.82
     propOrder
    -0.72
    mybatisplus
    -0.71
     الحره
    -0.69
    bootstrapcdn
    -0.66
    $_['
    -0.64
     Falun
    -0.63
    esgue
    -0.63
     BoxFit
    -0.63
    POSITIVE LOGITS
    Give
    0.51
     give
    0.50
     Give
    0.48
     acondicionado
    0.45
    give
    0.44
    نتاج
    0.41
     gâ
    0.40
    لكتر
    0.40
     cadrul
    0.40
    vateľ
    0.39
    Activations Density 1.749%

    No Known Activations