© 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. 6374
    Prev
    Next
    INDEX
    Explanations

    mentions of "National" followed by other words like "Institutes", "Center", or "Institute" and sometimes "of"

    oai_token-act-pair · gemini-2.0-flash

    patterns related to 'National'

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

    National

    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
    )))));
    -0.49
     Compra
    -0.38
     justo
    -0.36
    Discografia
    -0.35
    decre
    -0.35
    روابط
    -0.34
    dikan
    -0.34
     con
    -0.34
     juste
    -0.33
     camas
    -0.33
    POSITIVE LOGITS
     المعيارى
    0.93
    NameInMap
    0.85
     typelib
    0.84
     ivelany
    0.82
    ########.
    0.80
     تضيفلها
    0.79
     незавершена
    0.79
     שוליים
    0.77
    +#+#
    0.77
    Билгалдахарш
    0.77
    Activations Density 0.226%

    No Known Activations