© 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. 3760
    Prev
    Next
    INDEX
    Explanations

    content that provides additional information or structure, such as dates, lists, or text asides.

    oai_token-act-pair · gemini-2.0-flash

    unusual words

    np_max-act-logits · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ↵
    -0.45
    <eos>
    -0.42
    '
    -0.40
     (
    -0.39
    ↵↵
    -0.37
     "
    -0.31
     F
    -0.29
    ,
    -0.29
    .
    -0.29
      
    -0.28
    POSITIVE LOGITS
     enfans
    1.38
     estekak
    1.38
    KommentareTeilen
    1.34
     nahilalakip
    1.32
    ſelf
    1.30
    Personensuche
    1.29
     Efq
    1.28
     myſelf
    1.28
    تقاوى
    1.27
     $_"
    1.26
    Activations Density 5.045%

    No Known Activations