© 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. 7957
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific research and data analysis, especially around manual processes and percentages

    oai_token-act-pair · gemini-2.0-flash

    manual

    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
     AssemblyCulture
    -0.73
    Бахар
    -0.65
    GraphicsUnit
    -0.63
    новништво
    -0.60
    psum
    -0.60
    +:+
    -0.58
    WriteBarrier
    -0.57
    MessageTagHelper
    -0.56
    uminense
    -0.55
    AutoresizingMask
    -0.55
    POSITIVE LOGITS
     manual
    1.95
     manually
    1.90
     hand
    1.79
    manual
    1.75
    Manual
    1.70
     Manual
    1.70
     Manually
    1.56
    Manually
    1.50
     MANUAL
    1.48
     manuel
    1.44
    Activations Density 1.942%

    No Known Activations