© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 661
    Prev
    Next
    INDEX
    Explanations

    mentions of Jewish or Christian Zionism, and words that appear in proximity to the words Jew(s), Christian(s), and Israel

    oai_token-act-pair · gemini-2.0-flash

    country/nationality

    np_max-act-logits · gemini-2.0-flash

    say "places/nationalities"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.87
    ImageContext
    -0.67
     Confucian
    -0.64
    Personendaten
    -0.63
     myſelf
    -0.62
     Sanskrit
    -0.60
     uſed
    -0.57
    MigrationBuilder
    -0.57
     deleteUser
    -0.57
     PvP
    -0.56
    POSITIVE LOGITS
     german
    0.73
     india
    0.72
     american
    0.71
     australia
    0.71
     europe
    0.71
     french
    0.71
     america
    0.70
     european
    0.69
     canada
    0.69
     italian
    0.69
    Activations Density 7.069%

    No Known Activations