© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10390
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to respiratory and sleep-related medical conditions.

    oai_token-act-pair · gemini-2.0-flash

    breathing problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     breaths
    -0.97
     breathing
    -0.94
     breathe
    -0.92
     breath
    -0.91
     breathes
    -0.87
     Breathing
    -0.85
    Breathing
    -0.85
     respiratory
    -0.82
     Breath
    -0.81
    Respiratory
    -0.77
    POSITIVE LOGITS
     înd
    0.58
     '{@
    0.58
    tagHelperRunner
    0.57
    帖最后由
    0.54
     HasFactory
    0.54
     tartalomajánló
    0.53
    enerbahçe
    0.52
    
    0.51
     snippetHide
    0.51
     NUKAT
    0.51
    Activations Density 2.306%

    No Known Activations