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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12959
    Prev
    Next
    INDEX
    Explanations

    words related to resources and backup teams

    oai_token-act-pair · gemini-2.0-flash

    reserve

    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
    Not in Any Lists

    No Comments

    Negative Logits
     végétale
    -1.01
     asiatique
    -0.91
     étrangère
    -0.89
     culturelle
    -0.78
     étrangères
    -0.78
     fumée
    -0.77
     optique
    -0.77
     acrylique
    -0.75
     métallique
    -0.75
     grecque
    -0.75
    POSITIVE LOGITS
    鈥
    0.69
     television
    0.63
     disambiguazione
    0.63
    .–
    0.60
    —.
    0.60
    Mej
    0.60
    ism
    0.59
    —"
    0.57
     Eman
    0.57
    née
    0.57
    Activations Density 1.876%

    No Known Activations