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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8542
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "life" but aren't about biology

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Life
    -2.78
    Life
    -2.75
     life
    -2.70
     LIFE
    -2.67
    life
    -2.66
    LIFE
    -2.63
     lifetime
    -2.23
     lives
    -2.17
     vida
    -2.14
     lifes
    -2.08
    POSITIVE LOGITS
    Personendaten
    0.57
    RTEX
    0.56
    ServletException
    0.55
    twimg
    0.54
     ligiloj
    0.54
    CrossRef
    0.50
     nahilalakip
    0.49
    Hozzáférés
    0.48
     DBNull
    0.47
    ỡng
    0.46
    Activations Density 1.830%

    No Known Activations