© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16304
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are related to opinions, scientific studies or legal terminology

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     الدولى
    -0.69
     contd
    -0.65
     Efq
    -0.62
    SequentialGroup
    -0.61
    cipar
    -0.60
    sätzlich
    -0.58
     ་་
    -0.57
    gleiche
    -0.56
    berdayakan
    -0.56
    noons
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.59
    rungsseite
    0.59
     EconPapers
    0.56
    Xaml
    0.48
    removeAttr
    0.46
    RTLD
    0.45
    LookAnd
    0.45
     mahd
    0.45
     _$
    0.44
    INESS
    0.44
    Activations Density 13.530%

    No Known Activations