© 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. 11319
    Prev
    Next
    INDEX
    Explanations

    words and phrases from scientific texts and numeric entities, often relating to physics

    oai_token-act-pair · gemini-2.0-flash

    specialized vocabulary or technical terms

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

    Nuclear physics

    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
    UnusedPrivate
    -0.61
    atorics
    -0.55
    تقاوى
    -0.50
     Accountants
    -0.50
    Zeus
    -0.48
    ESSIONAL
    -0.47
    spunkt
    -0.47
     Anz
    -0.47
    Ů
    -0.46
    ścic
    -0.46
    POSITIVE LOGITS
     Administrativna
    0.67
    rungsseite
    0.66
    المناصب
    0.58
    يميديا
    0.54
     degradability
    0.53
     NSCoder
    0.50
    ground
    0.50
    endenza
    0.49
    setLayoutManager
    0.49
    yaret
    0.49
    Activations Density 1.505%

    No Known Activations