© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    dates and locations, especially in relation to political events in specific countries.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to geographic or political entities

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

    Zimbabwe Swaziland news

    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
    AndEndTag
    -1.01
     '\\;'
    -0.88
    contentLoaded
    -0.87
    windowFixed
    -0.79
    oa̍t
    -0.79
     myſelf
    -0.79
    tagHelperRunner
    -0.78
    spesies
    -0.77
     CreateTagHelper
    -0.77
    :✨
    -0.76
    POSITIVE LOGITS
    TagMode
    0.55
    Posted
    0.44
     state
    0.44
     new
    0.44
     de
    0.43
    Geplaatst
    0.42
     C
    0.41
     ca
    0.39
     B
    0.39
     san
    0.39
    Activations Density 0.477%

    No Known Activations