© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    the word "entire" or words that refer to completeness

    oai_token-act-pair · gemini-2.0-flash

    entire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     entire
    -1.76
     whole
    -1.52
    entire
    -1.51
     Entire
    -1.37
    whole
    -1.33
     ENTIRE
    -1.24
    Entire
    -1.20
    Whole
    -1.13
    <bos>
    -1.13
     WHOLE
    -1.05
    POSITIVE LOGITS
     CreateTagHelper
    0.83
     nakalista
    0.73
    Sucesor
    0.71
    tagext
    0.71
    UnusedPrivate
    0.63
    LayoutConstraint
    0.62
    RTHOOK
    0.62
     unknownFields
    0.62
     AssemblyProduct
    0.60
     resourceCulture
    0.59
    Activations Density 2.650%

    No Known Activations