© 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. 16070
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing," especially in scientific or technical texts, and sometimes associates with related words like "zed".

    oai_token-act-pair · 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
    Whilst
    -0.87
    Colours
    -0.81
    mybatisplus
    -0.80
    󠁢
    -0.79
     rhestr
    -0.79
     BoxFit
    -0.79
    anskje
    -0.78
    BagConstraints
    -0.77
     Organisations
    -0.77
     Whilst
    -0.75
    POSITIVE LOGITS
     chofe
    0.73
     harbor
    0.70
     himſelf
    0.68
     uſed
    0.66
     ſche
    0.66
     poffe
    0.66
     preſent
    0.66
     fhew
    0.65
     ſtate
    0.63
     purpoſe
    0.63
    Activations Density 0.826%

    No Known Activations