© 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. 15096
    Prev
    Next
    INDEX
    Explanations

    the word "sleep" and words associated with it, like "apnea", "airway", or "wave".

    oai_token-act-pair · gemini-2.0-flash

    sleep

    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
     sleeping
    -2.55
     Sleep
    -2.44
     sleep
    -2.42
     SLEEP
    -2.41
     slept
    -2.38
    Sleep
    -2.30
     Sleeping
    -2.23
     sleeps
    -2.22
    sleep
    -2.20
    sleeping
    -2.20
    POSITIVE LOGITS
     &___
    0.66
    Hochspringen
    0.63
    Enllaços
    0.59
    UnsafeEnabled
    0.57
    Ligações
    0.57
     Thesaurus
    0.56
     חיצוניים
    0.52
     SEDS
    0.52
     Winaray
    0.51
    enterOuterAlt
    0.51
    Activations Density 1.710%

    No Known Activations