© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9452
    Prev
    Next
    INDEX
    Explanations

    words that appear frequently in song lyrics and common phrases, perhaps as a way to identify sentiment

    oai_token-act-pair · gemini-2.0-flash

    relationships and emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    --)
    -0.53
    <bos>
    -0.53
    GeneratedMessage
    -0.50
    ]]
    -0.49
    WithMany
    -0.49
    ''')
    -0.49
     whist
    -0.48
    ніципа
    -0.48
     }}(\
    -0.48
    ונות
    -0.45
    POSITIVE LOGITS
    thâu
    0.66
    jsonwebtoken
    0.65
    aarrggbb
    0.62
    elemField
    0.56
    Życiorys
    0.53
     protoimpl
    0.52
    ittarius
    0.52
    sizeCache
    0.52
    setHorizontal
    0.51
    TypedDataSet
    0.51
    Activations Density 0.538%

    No Known Activations