© 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. 6955
    Prev
    Next
    INDEX
    Explanations

    the word "stock" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    stock

    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
     sentito
    -0.48
    àng
    -0.45
    ViewImports
    -0.43
    ิ้ง
    -0.41
     proposons
    -0.41
     hôte
    -0.41
     Meksiku
    -0.41
     createSlice
    -0.41
    endregion
    -0.41
     riconos
    -0.40
    POSITIVE LOGITS
     }}"></
    0.67
    
    0.66
    IsUnicode
    0.66
    dicionado
    0.62
    ={`/
    0.60
     saites
    0.60
    istik
    0.59
     Thra
    0.59
    -------------</
    0.59
     Portail
    0.57
    Activations Density 1.383%

    No Known Activations