© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14289
    Prev
    Next
    INDEX
    Explanations

    text that contains the biography of a dentist

    oai_token-act-pair · gemini-2.0-flash

    dental

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     practice
    -1.96
     Practice
    -1.76
    practice
    -1.73
    Practice
    -1.70
     practicing
    -1.66
     PRACTICE
    -1.62
     Practi
    -1.49
     practise
    -1.49
     practising
    -1.48
    PRACTICE
    -1.46
    POSITIVE LOGITS
     scolaires
    0.66
     réguli
    0.56
     sélectionnés
    0.55
     démocr
    0.55
     ImportError
    0.54
    veden
    0.53
     élevés
    0.53
     fédé
    0.52
     policiers
    0.51
    lass
    0.50
    Activations Density 0.643%

    No Known Activations