© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10702
    Prev
    Next
    INDEX
    Explanations

    a variety of words, often with shared letters like `a`, `e`, `i`, `o`, or `s` in specific sequences, without a clear unifying theme.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    initComponents
    -0.44
    opathie
    -0.43
     voilà
    -0.42
    <bos>
    -0.42
    errno
    -0.42
     tuyến
    -0.40
    Становништво
    -0.39
    SHIRE
    -0.39
    ую
    -0.39
    θεση
    -0.39
    POSITIVE LOGITS
     nahilalakip
    1.16
     kaarangay
    0.98
    wieś
    0.84
     चीज़ों
    0.81
    Personensuche
    0.81
    
    0.80
     تضيفلها
    0.76
    NOPQRST
    0.71
    webElementXpaths
    0.70
    GEBURTSDATUM
    0.70
    Activations Density 1.739%

    No Known Activations