© 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. 9239
    Prev
    Next
    INDEX
    Explanations

    mentions of proteins, residues, and mutations, often characterized by specific alphanumeric codes or labels used in scientific contexts.

    oai_token-act-pair · gemini-2.0-flash

    residues

    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
    "]/
    -0.63
     ſub
    -0.62
    )"),
    -0.61
    '},
    -0.61
     Shakspeare
    -0.60
     }}$}
    -0.60
     />';
    -0.59
     auffi
    -0.59
     himſelf
    -0.59
    NUMX
    -0.59
    POSITIVE LOGITS
    principalTable
    0.47
    ollectionView
    0.47
    така
    0.46
    香りが
    0.45
    Notae
    0.44
    +#+#
    0.43
     học
    0.42
    Fns
    0.42
     Foire
    0.41
     Италијани
    0.41
    Activations Density 1.495%

    No Known Activations