© 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. 950
    Prev
    Next
    INDEX
    Explanations

    information about healthcare, including names of hospitals, medical specialties, and people's titles in the medical field.

    oai_token-act-pair · gemini-2.0-flash

    hospitals

    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
    contentLoaded
    -0.56
    PerformLayout
    -0.56
    Cordialement
    -0.53
    buttonBar
    -0.53
    étaire
    -0.52
     ویکی‌پدیای
    -0.51
     OFDb
    -0.50
     Савезне
    -0.48
     carbon
    -0.48
    onné
    -0.48
    POSITIVE LOGITS
    CloseOperation
    0.59
    migrationBuilder
    0.54
    SpringBootTest
    0.52
    COUVER
    0.52
     Specialty
    0.52
     hueso
    0.52
     douleur
    0.51
    uckland
    0.51
     General
    0.48
    General
    0.46
    Activations Density 11.817%

    No Known Activations