© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10478
    Prev
    Next
    INDEX
    Explanations

    variations of the word "switch" and "turn" when used in a hardware-related context

    oai_token-act-pair · gemini-2.0-flash

    switch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     switch
    -1.87
     switched
    -1.71
     switching
    -1.66
     Switch
    -1.65
    Switch
    -1.59
    switch
    -1.58
     Switching
    -1.53
     switches
    -1.53
    Switching
    -1.51
     SWITCH
    -1.43
    POSITIVE LOGITS
    expandindo
    0.89
    SBATCH
    0.73
    AccessorTable
    0.68
     autorytatywna
    0.68
    __':
    0.63
    __":
    0.63
    colazione
    0.62
     onCreateView
    0.60
    CascadeType
    0.60
     shipwreck
    0.60
    Activations Density 1.089%

    No Known Activations