© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5217
    Prev
    Next
    INDEX
    Explanations

    instances of the word "entry" or the phrase "automatically entered" along with words or phrases related to surveys, questionnaires, or legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    data entry/access

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     entry
    -3.16
     Entry
    -3.14
    entry
    -2.92
     ENTRY
    -2.83
    Entry
    -2.83
     entries
    -2.83
     Entries
    -2.73
     entered
    -2.67
     enter
    -2.56
     entering
    -2.53
    POSITIVE LOGITS
     renovables
    0.40
    createServer
    0.40
     re
    0.37
    ColumnName
    0.37
    omatic
    0.36
    ocidade
    0.35
    mical
    0.35
    gtest
    0.34
    rxjs
    0.34
    IRQn
    0.34
    Activations Density 1.947%

    No Known Activations