© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3473
    Prev
    Next
    INDEX
    Explanations

    general filler words that relate to situations, time, and places with feelings

    oai_token-act-pair · gemini-2.0-flash

    Australia/Asia locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     chromatic
    -0.39
    AttributedString
    -0.38
    Pun
    -0.38
     Narr
    -0.38
     predicates
    -0.37
     mennes
    -0.37
     Pun
    -0.36
     ciphertext
    -0.36
     narrator
    -0.36
     potentiometer
    -0.36
    POSITIVE LOGITS
     Australia
    0.93
     Dhabi
    0.89
     Queensland
    0.89
     Brisbane
    0.89
     Singapore
    0.87
     Malaysia
    0.86
     Dubai
    0.86
     Hawaii
    0.85
     Malta
    0.85
     Australian
    0.84
    Activations Density 25.898%

    No Known Activations