© 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. 6432
    Prev
    Next
    INDEX
    Explanations

    words associated with coaches, certifications, and experience

    oai_token-act-pair · gemini-2.0-flash

    Business and coaching

    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
    驱
    -0.40
    श्व
    -0.40
    DRAG
    -0.40
     lái
    -0.40
    frees
    -0.39
    DispatchToProps
    -0.39
     सू
    -0.39
    償
    -0.39
     ModelExpression
    -0.38
     rutas
    -0.38
    POSITIVE LOGITS
    AsUp
    0.79
    expandindo
    0.79
     Paglinawan
    0.75
     chi̍t
    0.73
    IsContent
    0.68
    windowFixed
    0.68
    Personendaten
    0.65
    
    0.63
    IntoConstraints
    0.62
     ↔
    0.61
    Activations Density 0.639%

    No Known Activations