© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5611
    Prev
    Next
    INDEX
    Explanations

    non-standard english conjugations of the verb "to be" followed by verbs ending in "ing"

    oai_token-act-pair · gemini-2.0-flash

    internet text

    np_max-act-logits · gemini-2.0-flash

    text patterns from code or data types

    np_token-act-pair-logits · gpt-4o-mini
    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
     be
    -0.80
     disparu
    -0.61
     iNdEx
    -0.61
     estekak
    -0.60
    addGap
    -0.57
     Ảnh
    -0.56
    الحياه
    -0.55
     maschile
    -0.55
    več
    -0.55
     تضيفلها
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.56
    TypedDataSet
    0.52
    mi
    0.50
    TestTools
    0.48
     Mi
    0.45
     Al
    0.43
    JoinTable
    0.42
     Wi
    0.42
    ője
    0.41
     al
    0.40
    Activations Density 0.826%

    No Known Activations