© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10667
    Prev
    Next
    INDEX
    Explanations

    words that indicate awareness or acknowledgement

    oai_token-act-pair · gemini-2.0-flash

    Online articles and comments

    np_max-act-logits · gemini-2.0-flash

    say "nouns"

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     composizione
    -0.64
    !
    -0.50
     aukš
    -0.49
     composición
    -0.47
     voordeel
    -0.46
     quaisquer
    -0.45
     bahía
    -0.45
     concorda
    -0.45
     aihe
    -0.45
     žem
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    1.09
    tagHelperRunner
    0.85
    Vidite
    0.78
    WriteBarrier
    0.78
     numberWith
    0.72
     porno
    0.71
    BufferException
    0.69
    ibatis
    0.69
     cows
    0.69
     schist
    0.69
    Activations Density 7.512%

    No Known Activations