© 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. 6613
    Prev
    Next
    INDEX
    Explanations

    words related to scientific experiments and analysis

    oai_token-act-pair · gemini-2.0-flash

    performing

    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
     operacional
    -0.57
     regia
    -0.56
    cycline
    -0.55
    ixos
    -0.54
    numerusform
    -0.54
     GenerationType
    -0.52
    Crom
    -0.52
     المعيارى
    -0.52
    cyd
    -0.52
    phine
    -0.52
    POSITIVE LOGITS
     performing
    1.80
     perform
    1.79
     Perform
    1.71
    Perform
    1.68
     performs
    1.68
     performed
    1.66
    Performing
    1.56
     Performing
    1.54
    perform
    1.52
     PERFORM
    1.50
    Activations Density 5.429%

    No Known Activations