© 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. 10435
    Prev
    Next
    INDEX
    Explanations

    words related to conceptualizing and comprehending

    oai_token-act-pair · gemini-2.0-flash

    understand

    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
     Understand
    -1.17
     understood
    -1.14
     understand
    -1.14
    Understand
    -1.13
     understanding
    -1.04
     Understanding
    -1.03
    Understanding
    -1.01
    understand
    -1.00
     understands
    -1.00
    understood
    -0.94
    POSITIVE LOGITS
     resourceCulture
    0.76
     EconPapers
    0.73
    WriteTagHelper
    0.73
     चीज़ों
    0.71
    principalColumn
    0.69
    NullException
    0.66
    IntoConstraints
    0.65
    GeneratedCode
    0.64
     مرئيه
    0.64
    Източници
    0.61
    Activations Density 14.404%

    No Known Activations