© 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. 11433
    Prev
    Next
    INDEX
    Explanations

    forms of the word "learn".

    oai_token-act-pair · gemini-2.0-flash

    questions about learning

    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
    Aholisi
    -0.54
     learning
    -0.53
    orianCalendar
    -0.50
     Learning
    -0.50
    énario
    -0.49
    andır
    -0.49
     Escolar
    -0.49
     learn
    -0.48
    expandindo
    -0.47
     kasarigan
    -0.47
    POSITIVE LOGITS
     how
    1.08
     why
    0.81
     much
    0.70
     what
    0.70
     to
    0.70
    much
    0.66
     hvordan
    0.65
    how
    0.63
     which
    0.61
     cómo
    0.60
    Activations Density 0.944%

    No Known Activations