© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    content related to university admissions policies, especially affirmative action and diversity

    oai_token-act-pair · gemini-2.0-flash

    tokens related to affirmative action and diversity

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

    universities

    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
    adaptiveStyles
    -1.01
    setVerticalGroup
    -0.91
    Искәрмәләр
    -0.90
    GOTREF
    -0.87
    IntoConstraints
    -0.86
    WriteBarrier
    -0.85
    ValueStyle
    -0.83
     initComponents
    -0.82
    richTextPanel
    -0.81
    POSITIVE LOGITS
     fly
    0.45
    iseks
    0.43
    jeva
    0.40
    Ằ
    0.40
     l
    0.39
     Ekim
    0.38
     co
    0.38
    yethyl
    0.38
     volo
    0.37
    řád
    0.36
    Activations Density 1.813%

    No Known Activations