© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11790
    Prev
    Next
    INDEX
    Explanations

    complex AND logic is a heavy indicator, but it seems to activate on discussions of emotional expression, possibly in an academic context

    oai_token-act-pair · gemini-2.0-flash

    words related to emotions

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

    emotions

    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
     AspNetCore
    -0.71
    كويكب
    -0.54
    GNUC
    -0.50
    Literat
    -0.49
    PhysRevLett
    -0.49
     муніципалі
    -0.48
     فريبيس
    -0.48
    agot
    -0.48
    beda
    -0.48
    Hauptartikel
    -0.48
    POSITIVE LOGITS
     laughter
    0.84
     laughing
    0.78
     anger
    0.72
     giggles
    0.71
     laugh
    0.71
     laughs
    0.70
     tears
    0.69
     colère
    0.66
     sadness
    0.65
     funny
    0.65
    Activations Density 3.263%

    No Known Activations