© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14860
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology, especially related to anatomy and neurology

    oai_token-act-pair · gemini-2.0-flash

    anatomy and medical procedures

    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
    saraba
    -0.55
    Javadoc
    -0.50
     validamos
    -0.47
     miliardi
    -0.45
     informée
    -0.45
     lavable
    -0.43
    couz
    -0.42
     watched
    -0.42
    syms
    -0.42
     educated
    -0.41
    POSITIVE LOGITS
    strophy
    0.67
    ostomy
    0.61
    migrationBuilder
    0.60
    ElementException
    0.59
    TestingModule
    0.58
    monary
    0.55
    URLException
    0.54
    colgroup
    0.52
     foramen
    0.52
    lapsingToolbar
    0.52
    Activations Density 11.605%

    No Known Activations