© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as", with a bias towards "as well as"

    oai_token-act-pair · gemini-2.0-flash

    as

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    -0.56
    ’
    -0.55
    Whilst
    -0.53
    '
    -0.52
     Whilst
    -0.46
    ...
    -0.46
     IndexPath
    -0.45
     or
    -0.45
    oc
    -0.44
     kry
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.90
    NameInMap
    0.83
     تضيفلها
    0.79
     ivelany
    0.76
    PerformLayout
    0.75
     stället
    0.73
    Diweddarwch
    0.72
     متعلقه
    0.72
     Normdatei
    0.72
     daß
    0.70
    Activations Density 2.842%

    No Known Activations