© 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. 5623
    Prev
    Next
    INDEX
    Explanations

    conjunctions and pronouns within a sentence

    oai_token-act-pair · gemini-2.0-flash

    the word "in"

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

    "in" in different languages

    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
    expandindo
    -0.89
     ModelExpression
    -0.87
    IntoConstraints
    -0.87
    :✨
    -0.85
    .*")]
    -0.83
     GetEnumerator
    -0.82
     autorytatywna
    -0.78
    ItemBackground
    -0.76
    LookAnd
    -0.73
    ंदीखरीदारी
    -0.73
    POSITIVE LOGITS
     in
    2.39
     в
    1.29
    ใน
    1.27
     dalam
    1.22
     في
    1.10
     در
    1.07
     în
    1.06
     trong
    1.02
     In
    0.83
    dalam
    0.82
    Activations Density 10.093%

    No Known Activations