© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8767
    Prev
    Next
    INDEX
    Explanations

    words, often in other languages, with diacritics associated with them

    oai_token-act-pair · gemini-2.0-flash

    Code/gibberish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    va
    -0.65
    nu
    -0.57
     va
    -0.55
    gi
    -0.49
    Va
    -0.49
    леп
    -0.46
    vas
    -0.46
    OM
    -0.45
    endo
    -0.45
    bu
    -0.44
    POSITIVE LOGITS
     oprot
    0.87
     pinulongan
    0.79
    WriteBarrier
    0.78
    actionMode
    0.77
    Personendaten
    0.72
     propOrder
    0.71
     onAnimation
    0.69
    AndroidJUnit
    0.69
     millis
    0.68
    ValueStyle
    0.67
    Activations Density 14.354%

    No Known Activations