© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5945
    Prev
    Next
    INDEX
    Explanations

    harmonic or concord suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    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
    ع
    2.85
    з
    2.20
    !\!\
    2.15
    chic
    2.03
    علم
    2.02
    ch
    2.00
     infe
    1.94
     inactivation
    1.88
     soprattutto
    1.87
    л
    1.87
    POSITIVE LOGITS
     suspicion
    2.17
    स
    2.10
    Nowadays
    2.07
     footing
    2.04
    Leicester
    2.02
    な
    2.01
    सँग
    2.00
     suspicions
    1.98
     jury
    1.97
     договора
    1.97
    Activations Density 0.059%

    No Known Activations