© 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
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 13212
    Prev
    Next
    INDEX
    Explanations

    certain multi-letter sequences

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    offsetof
    -0.68
    AccessorTable
    -0.59
    MIDDLEWARE
    -0.59
    IMPORTED
    -0.54
     Cob
    -0.52
    simpleType
    -0.52
    Enllaces
    -0.50
     Kob
    -0.50
     isInitialized
    -0.50
     actionPerformed
    -0.49
    POSITIVE LOGITS
    kuuta
    0.77
    alama
    0.70
     AssemblyCulture
    0.66
    lam
    0.65
     chronique
    0.64
     Thirdly
    0.61
    lamp
    0.60
     lam
    0.60
    الحياه
    0.59
    resave
    0.59
    Activations Density 0.293%

    No Known Activations