© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8104
    Prev
    Next
    INDEX
    Explanations

    words that are associated with computer code

    oai_token-act-pair · gemini-2.0-flash

    Code/Logs

    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
    featureID
    -0.65
    WithMany
    -0.60
     Rukh
    -0.59
    ndice
    -0.58
     AssemblyTitle
    -0.57
    genstein
    -0.57
    LLocation
    -0.57
     Vieux
    -0.55
     DbContext
    -0.54
    RuleContext
    -0.54
    POSITIVE LOGITS
    oredCriteria
    0.63
     resourceCulture
    0.60
     useStyles
    0.57
    iocene
    0.54
    újo
    0.54
    alamualaikum
    0.53
    κτηρισ
    0.52
    Hochspringen
    0.52
    showLoading
    0.52
    Method
    0.52
    Activations Density 1.972%

    No Known Activations