© 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. 10662
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Java or C++, including keywords like "else", "catch", "new", "Override", parentheses, and curly braces

    oai_token-act-pair · gemini-2.0-flash

    programming keywords

    np_max-act · 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
    UnsafeEnabled
    -0.56
     gynhyrchwyd
    -0.54
     beginnetje
    -0.54
    
    -0.53
    CodeAttribute
    -0.52
    adaptiveStyles
    -0.50
     Roskov
    -0.46
     AssemblyCompany
    -0.45
    $_['
    -0.44
    ophan
    -0.44
    POSITIVE LOGITS
     disambiguazione
    0.72
    WindowConstants
    0.63
     newBuilder
    0.59
    ">//
    0.57
    ForRow
    0.55
    oredCriteria
    0.52
    Upload
    0.49
     Dirac
    0.48
     HOF
    0.47
     COE
    0.47
    Activations Density 3.239%

    No Known Activations