© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6598
    Prev
    Next
    INDEX
    Explanations

    the word "the", words or phrases that frequently precede or follow "the", superlatives, possession, quantities, or emphasis

    oai_token-act-pair · gemini-2.0-flash

    comparative adjectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     autorytatywna
    -0.67
    Demografía
    -0.59
    tvrt
    -0.57
    солю
    -0.56
     itſelf
    -0.56
     themſelves
    -0.56
     fhould
    -0.55
    wikidata
    -0.55
     beginnetje
    -0.54
    czyki
    -0.54
    POSITIVE LOGITS
     larger
    1.73
     stronger
    1.69
     bigger
    1.67
     smaller
    1.64
    larger
    1.63
    smaller
    1.63
     heavier
    1.61
    bigger
    1.52
    Larger
    1.51
     finer
    1.50
    Activations Density 2.394%

    No Known Activations