© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1157
    Prev
    Next
    INDEX
    Explanations

    words associated with luck and fortune

    oai_token-act-pair · gemini-2.0-flash

    luck/fortune

    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
     lucky
    -2.72
     fortunate
    -2.47
     luck
    -2.41
     LUCK
    -2.38
    lucky
    -2.36
     Lucky
    -2.31
    Lucky
    -2.28
     Luck
    -2.03
    LUCK
    -2.02
    luck
    -1.87
    POSITIVE LOGITS
    lms
    0.37
     pure
    0.35
     reinen
    0.34
    Ts
    0.33
    DataTypes
    0.33
    mming
    0.32
    wil
    0.32
     unre
    0.32
    nischer
    0.32
    ANAL
    0.32
    Activations Density 1.789%

    No Known Activations