© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    words and names related to the White House and politics

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with specific prefixes

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

    White House, political events

    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
    Personendaten
    -1.23
    AndEndTag
    -1.09
     '\\;'
    -1.05
    ValueStyle
    -0.98
     Taktlose
    -0.95
     Paglinawan
    -0.92
    ArrowToggle
    -0.91
     disambiguazione
    -0.91
     كومونز
    -0.88
    󠁢
    -0.88
    POSITIVE LOGITS
    int
    0.43
     cara
    0.40
     top
    0.37
    rug
    0.36
     da
    0.36
     Top
    0.35
    bat
    0.35
    ra
    0.35
     بال
    0.35
    劲
    0.34
    Activations Density 0.896%

    No Known Activations