© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6132
    Prev
    Next
    INDEX
    Explanations

    the word "capital" in the context of law, finance, and geography

    oai_token-act-pair · gemini-2.0-flash

    the term 'capital'

    np_token-act-pair-logits · gpt-4o-mini

    capital

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    脚注の使い方
    -0.58
    Personendaten
    -0.52
    migrationBuilder
    -0.51
    "}";
    -0.49
    elfth
    -0.47
    ValueStyle
    -0.47
    RenderAtEndOf
    -0.46
    GraphicsUnit
    -0.45
    ScopeManager
    -0.45
    TagMode
    -0.44
    POSITIVE LOGITS
    agaimana
    0.57
     NUKAT
    0.57
    ogenesis
    0.54
    leftrightarrow
    0.53
     breeches
    0.51
     booties
    0.50
    cdc
    0.50
     AppCompatTheme
    0.50
     OFDb
    0.50
    ulitis
    0.50
    Activations Density 0.922%

    No Known Activations