© 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. 12011
    Prev
    Next
    INDEX
    Explanations

    words that are found in research papers

    oai_token-act-pair · gemini-2.0-flash

    words indicating completeness or universality

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

    all

    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
     mehreren
    -0.56
    Several
    -0.55
    PropertyChanging
    -0.52
     qualcosa
    -0.52
     Several
    -0.52
     several
    -0.52
     mehrerer
    -0.51
     zweier
    -0.50
    archiviato
    -0.50
     Plusieurs
    -0.48
    POSITIVE LOGITS
     all
    2.31
    all
    1.62
     semua
    1.54
     every
    1.45
     todas
    1.44
     each
    1.42
     ALL
    1.41
     toutes
    1.36
     todos
    1.33
     все
    1.32
    Activations Density 6.737%

    No Known Activations