© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6331
    Prev
    Next
    INDEX
    Explanations

    words related to pulmonary and cardiovascular medical conditions, and medical interventions.

    oai_token-act-pair · gemini-2.0-flash

    pulmonary medical terms

    np_token-act-pair-logits · gpt-4o-mini

    Medical and pulmonary issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     myſelf
    -1.16
     Monfieur
    -1.10
     Theſe
    -1.10
    SBATCH
    -1.09
     itſelf
    -1.08
     ſeveral
    -0.98
     whoſe
    -0.98
     becauſe
    -0.98
     uſed
    -0.98
     pleaſure
    -0.97
    POSITIVE LOGITS
     DNA
    0.55
     (
    0.54
     "
    0.54
     Cap
    0.54
     
    0.53
     mu
    0.50
     Z
    0.49
     and
    0.49
    </strong>
    0.48
     of
    0.48
    Activations Density 2.184%

    No Known Activations