© 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. 16208
    Prev
    Next
    INDEX
    Explanations

    python code related to a robot named Nao

    oai_token-act-pair · 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
    IsPostBack
    -0.59
    っこう
    -0.52
    ponses
    -0.49
    RunAsync
    -0.48
    ethene
    -0.47
     Michael
    -0.47
    charpe
    -0.46
    arrings
    -0.45
     Vitro
    -0.45
    gorov
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.68
    UnusedPrivate
    0.65
     estekak
    0.63
     EconPapers
    0.61
     ModelExpression
    0.59
     Lleva
    0.58
     متحده
    0.57
     CreateTagHelper
    0.56
    出版年
    0.55
    :✨
    0.55
    Activations Density 1.468%

    No Known Activations