© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4638
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terminology

    oai_token-act-pair · gemini-2.0-flash

    Statistical analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     externi
    -0.65
    InjectAttribute
    -0.62
    bitField
    -0.55
    archiviato
    -0.55
     sẻ
    -0.55
    bParam
    -0.49
    thâu
    -0.49
    DebuggerStep
    -0.48
     ModelExpression
    -0.48
    Bele
    -0.47
    POSITIVE LOGITS
     statistical
    0.91
     differences
    0.84
     difference
    0.81
     statistically
    0.81
    Statistical
    0.79
    stats
    0.78
     Statistical
    0.78
     statistics
    0.77
     Differences
    0.74
    stat
    0.71
    Activations Density 3.967%

    No Known Activations