© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    terms and names related to a specific game or software framework.

    oai_token-act-pair · gemini-2.0-flash

    code related terms

    np_max-act · 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
    Negative Logits
    esterday
    -0.84
    Portale
    -0.82
    SPATH
    -0.79
    ImageBackground
    -0.74
    bourhood
    -0.73
    hirts
    -0.72
    ✨:
    -0.71
    ROIT
    -0.69
    XXI
    -0.67
    phosa
    -0.67
    POSITIVE LOGITS
     kock
    0.65
     culturelles
    0.63
     normaux
    0.60
     nationaux
    0.58
     nubes
    0.57
     pattes
    0.57
     løpet
    0.56
     doppio
    0.56
     vaisselle
    0.56
     legales
    0.56
    Activations Density 1.411%

    No Known Activations