© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4624
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to formal documentation, especially in an institutional setting.

    oai_token-act-pair · gemini-2.0-flash

    Writing actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     EconPapers
    -0.93
     HasFactory
    -0.66
    cshtml
    -0.66
    DOCTYPE
    -0.64
     MaterialApp
    -0.62
     autorytatywna
    -0.61
     cherchés
    -0.60
    évaluateur
    -0.60
     riuscito
    -0.60
     ProtoMessage
    -0.59
    POSITIVE LOGITS
     hand
    0.66
    fill
    0.66
     fill
    0.65
    Hand
    0.57
     Fill
    0.56
     Hand
    0.55
    CloseOperation
    0.55
    hand
    0.55
    Fill
    0.55
    fills
    0.54
    Activations Density 3.359%

    No Known Activations