© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9867
    Prev
    Next
    INDEX
    Explanations

    context words, conjunctions, and punctuation with some dates mixed in.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     several
    -2.00
     algunos
    -1.99
     many
    -1.98
    several
    -1.97
     alguns
    -1.97
    algunos
    -1.94
     beberapa
    -1.90
     some
    -1.90
     Several
    -1.88
    Several
    -1.87
    POSITIVE LOGITS
    ashe
    0.41
    tze
    0.37
    OnAdd
    0.37
    omores
    0.36
     tpl
    0.35
    туры
    0.35
    нов
    0.35
    אה
    0.34
    kei
    0.34
     đều
    0.34
    Activations Density 6.434%

    No Known Activations