© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7379
    Prev
    Next
    INDEX
    Explanations

    mentions of astronomical objects

    oai_token-act-pair · gemini-2.0-flash

    moon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.90
    GEBURTSDATUM
    -0.86
     moon
    -0.79
     transfieras
    -0.74
     Roskov
    -0.70
     planets
    -0.70
    moon
    -0.70
     MOON
    -0.69
     disambiguazione
    -0.69
    MOON
    -0.68
    POSITIVE LOGITS
    observe
    0.42
     mare
    0.39
     chí
    0.38
     huéspedes
    0.38
    Guten
    0.38
    toPromise
    0.38
     месяц
    0.36
    த
    0.36
    λή
    0.36
     aí
    0.35
    Activations Density 0.587%

    No Known Activations