© 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. 257
    Prev
    Next
    INDEX
    Explanations

    words and phrases generally related to healthcare, policy and company names

    oai_token-act-pair · gemini-2.0-flash

    say health

    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
     health
    -3.06
    Health
    -3.03
     Health
    -3.00
    health
    -2.94
     HEALTH
    -2.83
    HEALTH
    -2.78
     healthier
    -2.30
    Healthy
    -2.28
     healthy
    -2.27
    healthy
    -2.20
    POSITIVE LOGITS
    jsxFileName
    0.54
    :✨
    0.48
    
    0.48
    SaveChangesAsync
    0.48
     चीज़ों
    0.47
     án
    0.46
     pageable
    0.46
    adaptiveStyles
    0.46
    DoubleQuotes
    0.45
    ActionPerformed
    0.45
    Activations Density 2.076%

    No Known Activations