© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time period or tense

    oai_token-act-pair · gemini-2.0-flash

    History and political science

    np_max-act-logits · gemini-2.0-flash

    say "historical periods" Method used: 2 — pattern in tokens after; explanation: say "historical periods"

    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_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
     persil
    -0.47
     cached
    -0.47
    own
    -0.46
    DoubleQuotes
    -0.45
     بلد
    -0.42
    gios
    -0.40
    cached
    -0.40
     trúc
    -0.39
     Matt
    -0.39
     Unburied
    -0.39
    POSITIVE LOGITS
    httphttps
    0.93
    ngdoc
    0.88
    出版年
    0.83
    localctx
    0.83
    contentLoaded
    0.80
     Industrial
    0.78
    '},
    0.77
    Industrial
    0.75
    RenderAtEndOf
    0.75
     INDUSTRIAL
    0.73
    Activations Density 2.304%

    No Known Activations