© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4698
    Prev
    Next
    INDEX
    Explanations

    words related to selection in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     selection
    -1.06
     Selection
    -0.97
    selection
    -0.93
     selecting
    -0.89
    Selection
    -0.89
     selected
    -0.84
     Selecting
    -0.82
     SELECTION
    -0.81
     selección
    -0.80
     select
    -0.79
    POSITIVE LOGITS
    Hauptartikel
    0.80
    ArgsConstructor
    0.75
    MemoryWarning
    0.72
    UnusedPrivate
    0.69
     שוליים
    0.69
     AssemblyCompany
    0.69
    ViewImports
    0.68
    XmlType
    0.68
     resourceCulture
    0.67
     Roskov
    0.66
    Activations Density 38.590%

    No Known Activations