© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12170
    Prev
    Next
    INDEX
    Explanations

    personal stories of learning a skill

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'learn'

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

    learn

    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
     fly
    -0.50
    metrist
    -0.50
    astéro
    -0.50
    calientes
    -0.48
     GenerationType
    -0.47
     StatefulWidget
    -0.47
    ุ่ม
    -0.47
     Medicine
    -0.47
    yntaxException
    -0.47
    Personendaten
    -0.45
    POSITIVE LOGITS
     learn
    1.91
     learning
    1.84
     learned
    1.84
     learns
    1.78
    learn
    1.65
     LEARN
    1.61
     learnt
    1.61
    learning
    1.59
    learned
    1.57
     Learn
    1.52
    Activations Density 1.708%

    No Known Activations