© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6616
    Prev
    Next
    INDEX
    Explanations

    words related to government, ownership, and property

    oai_token-act-pair · gemini-2.0-flash

    law

    np_max-act · gemini-2.0-flash

    say "punctuation/whitespace" Method used: 2 — because following tokens are quotes, commas, brackets, or space-prefixed tokens; say "punctuation/whitespace"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    of
    -0.60
     tré
    -0.58
     ur
    -0.54
     some
    -0.53
    id
    -0.53
    ops
    -0.52
    zetten
    -0.52
     mit
    -0.51
    ofy
    -0.50
    最快更新
    -0.50
    POSITIVE LOGITS
     propOrder
    1.19
     nakalista
    1.05
    TagMode
    0.94
    mybatisplus
    0.87
    WriteBarrier
    0.84
     ThemeData
    0.84
     ſche
    0.81
    ValueGeneration
    0.81
    出版年
    0.80
     leçon
    0.79
    Activations Density 2.919%

    No Known Activations