© 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. 11508
    Prev
    Next
    INDEX
    Explanations

    words related to arguments, disagreements, and legal disputes

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'by'

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

    action or opinion *by* someone

    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
    ^(@)
    -1.07
     Efq
    -1.01
     ―――――
    -1.01
    MigrationBuilder
    -0.94
     ſind
    -0.90
    脚注の使い方
    -0.88
     auffi
    -0.88
     Theſe
    -0.88
     hindurch
    -0.88
    GEBURTSDATUM
    -0.87
    POSITIVE LOGITS
     by
    2.77
    by
    2.00
     oleh
    1.95
     By
    1.58
    By
    1.45
     BY
    1.45
     توسط
    1.41
     pela
    1.33
     przez
    1.28
     bởi
    1.25
    Activations Density 2.550%

    No Known Activations