© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5390
    Prev
    Next
    INDEX
    Explanations

    the word "step" appearing in a variety of contexts, sometimes paired with words related to family or governance

    oai_token-act-pair · gemini-2.0-flash

    First Lady or first step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     honours
    -0.70
     (£
    -0.66
     Unito
    -0.65
     Whilst
    -0.64
     GCSE
    -0.63
     recognise
    -0.62
     MainAxisSize
    -0.61
    obses
    -0.60
     encyclo
    -0.60
    splat
    -0.59
    POSITIVE LOGITS
    SourceChecksum
    0.78
     CreateTagHelper
    0.61
     communiquez
    0.56
    ientôt
    0.56
     vectorielles
    0.56
     cardiaque
    0.56
    outSlope
    0.55
     répondit
    0.55
     esposo
    0.54
     acrylique
    0.54
    Activations Density 1.696%

    No Known Activations