© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13790
    Prev
    Next
    INDEX
    Explanations

    passive verbs, often used to indicate something is known or proven

    oai_token-act-pair · gemini-2.0-flash

    say "by"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     <=",
    -0.84
    ButterKnife
    -0.76
     estekak
    -0.73
     חיצוניים
    -0.72
     >=",
    -0.71
    aarrggbb
    -0.70
     AttributeSet
    -0.65
    rmtree
    -0.64
     يتيمه
    -0.64
     '\\;'
    -0.63
    POSITIVE LOGITS
     by
    1.23
     oleh
    0.77
    by
    0.74
     By
    0.62
    By
    0.61
     durch
    0.59
     pamamagitan
    0.56
     through
    0.54
    getBy
    0.52
     svým
    0.50
    Activations Density 1.334%

    No Known Activations