© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4280
    Prev
    Next
    INDEX
    Explanations

    the word "retire" and its derivatives

    oai_token-act-pair · gemini-2.0-flash

    retire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     retirement
    -2.36
     retire
    -2.30
     retired
    -2.17
    retirement
    -2.02
     Retirement
    -2.02
     retiring
    -1.98
     retires
    -1.91
    Retirement
    -1.91
    retired
    -1.87
     Retired
    -1.84
    POSITIVE LOGITS
    rungsseite
    0.65
    MigrationBuilder
    0.63
     Nigeria
    0.60
    PRWEB
    0.58
     Wikimedijinoj
    0.57
     Wiktionnaire
    0.56
     للاسماء
    0.56
     Nigerian
    0.55
    momix
    0.55
     zape
    0.54
    Activations Density 5.471%

    No Known Activations