© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8141
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in legal and/or scientific writing

    oai_token-act-pair · gemini-2.0-flash

    legal and mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    posedge
    -0.58
     almendras
    -0.46
     gereken
    -0.42
     fibra
    -0.39
     fibras
    -0.39
    So
    -0.38
    @
    -0.38
     spil
    -0.37
     nueces
    -0.37
     цели
    -0.37
    POSITIVE LOGITS
    脚注の使い方
    0.88
    AccessorTable
    0.87
     noDo
    0.85
    rungsseite
    0.82
    twimg
    0.81
     تضيفلها
    0.79
     ligiloj
    0.78
    adaptiveStyles
    0.78
    featureID
    0.76
     >=",
    0.76
    Activations Density 1.907%

    No Known Activations