© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9219
    Prev
    Next
    INDEX
    Explanations

    technical language related to chemical compounds and minerals

    oai_token-act-pair · gemini-2.0-flash

    Chemicals and minerals

    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
     calcium
    -0.86
    fjspx
    -0.85
    calcium
    -0.81
     Calcium
    -0.80
     oxygen
    -0.79
     nutrients
    -0.77
     Nitrogen
    -0.75
     potassium
    -0.75
     Oxygen
    -0.74
    iotensin
    -0.73
    POSITIVE LOGITS
    UserScript
    0.54
    basicConfig
    0.47
    bootstrapcdn
    0.43
    Билгалдахарш
    0.42
     behavior
    0.41
    mybatisplus
    0.41
    antd
    0.40
    stdarg
    0.40
     laughter
    0.40
     Waray
    0.40
    Activations Density 13.334%

    No Known Activations