© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    scientific studies and their statistical results

    oai_token-act-pair · gemini-2.0-flash

    words related to association and relationships

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

    association

    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
     Roskov
    -0.61
    nationality
    -0.60
    Демографія
    -0.60
     NSCoder
    -0.57
    merking
    -0.57
    Tikang
    -0.57
    PASO
    -0.56
    Mediabestanden
    -0.55
     Lagrange
    -0.54
     commerciales
    -0.54
    POSITIVE LOGITS
     association
    1.23
     associations
    0.98
     associated
    0.97
    association
    0.88
    associated
    0.84
    Associations
    0.82
    Association
    0.81
     associ
    0.81
     asociación
    0.80
     relationship
    0.79
    Activations Density 4.808%

    No Known Activations