© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2665
    Prev
    Next
    INDEX
    Explanations

    occurrences of "a," "the," "and," "is," "had," and "third"

    oai_token-act-pair · gemini-2.0-flash

    third

    np_max-act-logits · gemini-2.0-flash

    say "ordinal numbers" Method used: 2 — tokens after show ordinals/numeric positions — say "ordinal numbers"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Second
    -0.56
     second
    -0.52
    Second
    -0.51
     SECOND
    -0.50
     Второй
    -0.49
    HomeAsUp
    -0.47
    Segundo
    -0.46
     Kedua
    -0.46
     Segundo
    -0.45
     two
    -0.45
    POSITIVE LOGITS
     third
    2.08
    third
    1.98
    Third
    1.95
     Third
    1.94
     THIRD
    1.67
     thirds
    1.63
     Thirdly
    1.55
    THIRD
    1.55
    第三
    1.54
    thirds
    1.52
    Activations Density 3.285%

    No Known Activations