© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2817
    Prev
    Next
    INDEX
    Explanations

    words related to academic settings, clinical practice, and research

    oai_token-act-pair · gemini-2.0-flash

    say "practice"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -3.45
     Practice
    -3.30
    Practice
    -3.16
    practice
    -3.13
     PRACTICE
    -3.09
     practise
    -3.06
     practicing
    -2.95
     practiced
    -2.92
     practising
    -2.81
     practised
    -2.78
    POSITIVE LOGITS
    kloped
    0.48
     lauf
    0.47
    ovací
    0.42
    ódó
    0.39
    ambiguation
    0.38
     الحره
    0.38
    unyai
    0.38
    keyed
    0.38
    ľov
    0.38
     AssemblyProduct
    0.37
    Activations Density 1.513%

    No Known Activations