© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 433
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المستخدم
    0.55
     До
    0.55
    До
    0.55
     utilisé
    0.53
     utilisée
    0.52
     Д
    0.51
    де
    0.51
    Likewise
    0.50
     }{}_{\
    0.49
    Aloe
    0.49
    POSITIVE LOGITS
     gleaned
    0.97
    :
    0.93
     lurking
    0.89
     arising
    0.89
     regarding
    0.83
     reiterated
    0.80
     사항
    0.77
     stemming
    0.77
     fraught
    0.75
     outlined
    0.75
    Activations Density 3.520%

    No Known Activations