© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1787
    Prev
    Next
    INDEX
    Explanations

    adjectives and comparative adjectives, especially those relating to size, health and negative emotions

    oai_token-act-pair · gemini-2.0-flash

    comparative adjectives ending in 'er'

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

    er/ier suffixes

    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
    Negative Logits
     незавершена
    -1.20
     nakalista
    -1.05
     Мексичка
    -0.91
     ProtoMessage
    -0.90
    SharedCtor
    -0.88
     <=",
    -0.88
     تضيفلها
    -0.85
    complexContent
    -0.85
    Autoritní
    -0.84
    bootstrapcdn
    -0.84
    POSITIVE LOGITS
    ier
    1.22
    lier
    1.13
     hơn
    1.08
    تر
    1.05
    er
    0.97
     تر
    0.93
    nier
    0.91
    cier
    0.90
    IER
    0.90
    der
    0.90
    Activations Density 0.761%

    No Known Activations