© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10617
    Prev
    Next
    INDEX
    Explanations

    code comments labeled "TODO" or lines of code where a function is returning a value

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     major
    -0.67
     return
    -0.63
     per
    -0.61
    ра
    -0.56
    es
    -0.54
     or
    -0.54
     use
    -0.53
     total
    -0.53
     ter
    -0.53
     am
    -0.53
    POSITIVE LOGITS
     pinulongan
    0.98
    oredCriteria
    0.97
     AssemblyVersion
    0.97
     otomatig
    0.94
     estimés
    0.93
     AssemblyCulture
    0.92
     '\\;'
    0.91
     Italijani
    0.90
     réguli
    0.89
    Gön
    0.89
    Activations Density 0.706%

    No Known Activations