© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2371
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transduction
    0.73
    աց
    0.68
    篑
    0.68
     Covington
    0.66
     πρόσ
    0.66
    彫
    0.65
     آہستہ
    0.64
     благодар
    0.64
    組み立て
    0.63
     Lala
    0.63
    POSITIVE LOGITS
     ==
    2.55
     !=
    2.45
    ==
    2.17
    equals
    2.16
     isEqual
    2.16
    =='
    2.09
    !=
    2.09
     equals
    2.08
    =="
    2.05
     =='
    2.03
    Activations Density 0.128%

    No Known Activations