© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 413
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and necessity

    oai_token-act-pair · gemini-2.0-flash

    Various writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disponibilités
    -0.81
    Parcelize
    -0.79
    WriteTagHelper
    -0.76
     ujednoznacz
    -0.75
     itſelf
    -0.73
    moiselle
    -0.73
     InputDecoration
    -0.72
     themſelves
    -0.69
     الاطلاع
    -0.69
    derry
    -0.68
    POSITIVE LOGITS
    Nadie
    0.44
    everything
    0.43
     tudo
    0.43
     everything
    0.41
    hnia
    0.40
    ToolStrip
    0.40
    Everything
    0.39
     Roskov
    0.39
    хьтан
    0.39
     wissen
    0.39
    Activations Density 1.756%

    No Known Activations